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. 13535
    Prev
    Next
    INDEX
    Explanations

    a series of related events or incidents

    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
    +0.28
    1.5%
    393
    +0.20
    1.1%
    561
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.28
    0.23
    608
    +0.20
    0.16
    362
    +0.09
    0.10
    Negative Logits
    uca
    -0.68
    arers
    -0.63
    vale
    -0.58
    Mob
    -0.57
    Sport
    -0.56
    orporated
    -0.55
    esse
    -0.54
    alty
    -0.53
    Football
    -0.53
    zu
    -0.52
    POSITIVE LOGITS
     events
    0.74
     successive
    0.71
     steps
    0.68
     alternating
    0.65
     consecutive
    0.65
     succession
    0.64
     posts
    0.64
     episodes
    0.63
     setbacks
    0.62
     overlapping
    0.62
    Activations Density 8.409%

    No Known Activations