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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 45553
    Prev
    Next
    INDEX
    Explanations

    information related to online events or updates in various fields like technology, entertainment, and community activities

    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
    +0.25
    1.3%
    640
    +0.12
    0.6%
    6
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.21
    6
    +0.12
    0.13
    679
    +0.10
    0.18
    Negative Logits
    undai
    -0.73
    yrus
    -0.65
    itated
    -0.64
     footing
    -0.63
    mber
    -0.63
    ems
    -0.63
    apeshifter
    -0.62
    ©¶æ
    -0.60
     intestine
    -0.60
     scorp
    -0.60
    POSITIVE LOGITS
    @#&
    1.11
     :)
    1.03
     ;)
    0.91
     :-)
    0.87
     ðŁĻĤ
    0.85
    ?!
    0.85
     Featuring
    0.82
     ðŁĺ
    0.81
     Come
    0.80
    #$
    0.79
    Activations Density 9.681%

    No Known Activations