© 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. 33098
    Prev
    Next
    INDEX
    Explanations

    proper nouns (names of people)

    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
    +0.21
    1.0%
    643
    +0.12
    0.6%
    430
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.21
    0.08
    346
    +0.12
    0.09
    141
    +0.10
    0.07
    Negative Logits
    packing
    -0.79
     actionGroup
    -0.78
    urbed
    -0.70
    ĺħ
    -0.70
    cery
    -0.70
    onder
    -0.67
    STER
    -0.67
    opsy
    -0.66
    isode
    -0.66
    req
    -0.64
    POSITIVE LOGITS
    ity
    0.87
     Boone
    0.82
     Patrick
    0.81
     Webster
    0.80
     Bryan
    0.80
     Corm
    0.76
     Kahn
    0.76
     Hann
    0.75
    ildo
    0.72
     Daniel
    0.72
    Activations Density 5.523%

    No Known Activations