© 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. 45958
    Prev
    Next
    INDEX
    Explanations

    technical terms or code-related phrases

    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
    466
    +0.13
    0.5%
    41
    +0.12
    0.5%
    711
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.13
    0.11
    556
    +0.12
    0.09
    46
    +0.11
    0.07
    Negative Logits
     Samoa
    -0.81
    etheless
    -0.79
    anwhile
    -0.72
     Jinn
    -0.69
     Reincarn
    -0.68
    vironment
    -0.68
    ãĥŁ
    -0.67
    agascar
    -0.67
     Seasons
    -0.65
     outwe
    -0.65
    POSITIVE LOGITS
    pling
    0.79
    Ly
    0.75
    itte
    0.74
    interstitial
    0.72
     Bolton
    0.69
    pole
    0.69
    ledge
    0.68
    gaard
    0.67
    ounge
    0.66
    pg
    0.65
    Activations Density 17.132%

    No Known Activations