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. 45407
    Prev
    Next
    INDEX
    Explanations

    information related to legal documents and financial transactions

    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
    1.1%
    481
    +0.07
    0.5%
    336
    +0.06
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.15
    0.48
    138
    +0.07
    0.46
    64
    +0.06
    -0.20
    Negative Logits
    taboola
    -0.48
     srfAttach
    -0.43
    tyard
    -0.42
    fried
    -0.41
     thous
    -0.41
     WATCHED
    -0.40
    isec
    -0.40
    amaz
    -0.39
    rimp
    -0.38
     Huck
    -0.38
    POSITIVE LOGITS
    Ds
    0.46
    amily
    0.44
    Gs
    0.43
    olitics
    0.39
    UE
    0.39
    Ms
    0.39
    ipolar
    0.39
    HY
    0.38
    Asset
    0.38
     analges
    0.38
    Activations Density 11.214%

    No Known Activations