© 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. 32970
    Prev
    Next
    INDEX
    Explanations

    words related to programming languages and writing code

    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
    +0.18
    0.7%
    542
    +0.12
    0.5%
    624
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.18
    0.10
    471
    +0.12
    0.08
    161
    +0.11
    0.04
    Negative Logits
    enei
    -0.92
    anship
    -0.86
    ply
    -0.82
    annot
    -0.82
    abre
    -0.79
    asionally
    -0.76
    vette
    -0.76
    ane
    -0.76
    assert
    -0.75
    pan
    -0.75
    POSITIVE LOGITS
     closest
    0.77
    iest
    0.76
     Restore
    0.74
     itself
    0.74
    liest
    0.73
     nearest
    0.71
     Alc
    0.71
     hardest
    0.71
    ACTED
    0.70
     resides
    0.70
    Activations Density 17.559%

    No Known Activations