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. 13317
    Prev
    Next
    INDEX
    Explanations

    instances of copyright infringement and related legal terms

    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
    +0.23
    1.0%
    137
    +0.13
    0.6%
    151
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    711
    +0.23
    0.04
    137
    +0.13
    0.04
    549
    +0.13
    0.06
    Negative Logits
    ellen
    -0.88
     Anthrop
    -0.83
    ilde
    -0.81
    hani
    -0.80
     Anchorage
    -0.80
    agan
    -0.78
     Belt
    -0.75
     Ket
    -0.72
    belt
    -0.72
    ollower
    -0.71
    POSITIVE LOGITS
     infringement
    1.45
     infring
    1.32
     infringing
    1.19
    yright
    1.14
    yrights
    1.12
     copyright
    0.97
     royalties
    0.94
     copyrighted
    0.93
    ãĤº
    0.89
     notices
    0.88
    Activations Density 9.460%

    No Known Activations