© 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. 35971
    Prev
    Next
    INDEX
    Explanations

    legal and official documents and filings

    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
    +0.15
    0.7%
    654
    +0.13
    0.6%
    487
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.15
    0.27
    180
    +0.13
    0.06
    393
    +0.10
    0.28
    Negative Logits
    oured
    -0.79
    ours
    -0.69
    peak
    -0.67
    oren
    -0.62
    ateurs
    -0.61
     taught
    -0.61
    ory
    -0.59
     steered
    -0.59
    awar
    -0.58
     sacrificing
    -0.58
    POSITIVE LOGITS
     paperwork
    0.89
     complaint
    0.81
    idav
    0.79
     lawsuit
    0.77
     FIR
    0.74
     registration
    0.74
     papers
    0.74
     arbitration
    0.72
     FOIA
    0.71
     registry
    0.71
    Activations Density 14.362%

    No Known Activations