Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 13373
    Prev
    Next
    INDEX
    Explanations

    references to military units, personnel, and organizational structures

    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
    +0.19
    0.9%
    267
    +0.12
    0.6%
    420
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    585
    +0.19
    0.10
    146
    +0.12
    0.08
    598
    +0.11
    0.04
    Negative Logits
    acious
    -0.88
     guiActiveUn
    -0.86
    arching
    -0.80
    hod
    -0.79
    itching
    -0.73
    aciously
    -0.73
    itely
    -0.72
    essage
    -0.69
    iscopal
    -0.69
    ifying
    -0.69
    POSITIVE LOGITS
     Ltd
    0.79
     Massacre
    0.78
    ptives
    0.78
     Limited
    0.74
     Reports
    0.74
     Publishers
    0.73
     Fathers
    0.72
     Ships
    0.72
    uria
    0.70
     Hath
    0.68
    Activations Density 8.506%

    No Known Activations