© 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. 32070
    Prev
    Next
    INDEX
    Explanations

    mentions of specific military corps or related entities

    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
    +0.14
    0.9%
    288
    +0.09
    0.5%
    659
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    498
    +0.14
    0.08
    644
    +0.09
    0.08
    561
    +0.07
    0.07
    Negative Logits
    izer
    -0.49
    âĹ¼
    -0.49
    èª
    -0.49
    selves
    -0.49
    ãĥĥãĤ¯
    -0.46
    ãĥĥ
    -0.46
    ead
    -0.45
    ãĤ¯
    -0.44
    izophren
    -0.44
    package
    -0.44
    POSITIVE LOGITS
    naire
    0.71
    ombat
    0.62
     Corps
    0.59
    anova
    0.57
     Headquarters
    0.56
    eteria
    0.56
    naires
    0.56
    erness
    0.54
    quit
    0.54
    xon
    0.53
    Activations Density 6.978%

    No Known Activations