© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 35334
    Prev
    Next
    INDEX
    Explanations

    information related to political events and conflicts, particularly focusing on statements and actions by government officials and organizations

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.21
    1.1%
    640
    +0.11
    0.6%
    240
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.21
    0.28
    393
    +0.11
    0.26
    745
    +0.09
    -0.13
    Negative Logits
     favor
    -0.74
     scrimmage
    -0.71
     muse
    -0.63
     grades
    -0.62
     prelim
    -0.61
     finished
    -0.61
     Saiyan
    -0.61
     Zen
    -0.60
     Mystic
    -0.58
     adjud
    -0.58
    POSITIVE LOGITS
    We
    1.11
    Our
    1.06
    There
    1.05
    Therefore
    1.03
    It
    1.03
    Given
    1.01
    Clearly
    0.99
    Otherwise
    0.99
    They
    0.98
    Today
    0.97
    Activations Density 11.848%

    No Known Activations