© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 45852
    Prev
    Next
    INDEX
    Explanations

    percentages or proportions related to a specified group or category

    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
    +0.14
    0.7%
    314
    +0.11
    0.6%
    485
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.14
    0.23
    608
    +0.11
    0.15
    362
    +0.10
    0.10
    Negative Logits
    urn
    -0.70
     resil
    -0.66
    acid
    -0.65
    ires
    -0.60
    jab
    -0.60
    BuyableInstoreAndOnline
    -0.60
    jen
    -0.58
    soever
    -0.57
    rouse
    -0.57
    iked
    -0.56
    POSITIVE LOGITS
     variance
    0.66
    imental
    0.65
    ority
    0.65
    vich
    0.61
    anni
    0.57
     billions
    0.56
    vantage
    0.55
     differences
    0.54
     halftime
    0.53
     variation
    0.53
    Activations Density 8.073%

    No Known Activations