© 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. 34753
    Prev
    Next
    INDEX
    Explanations

    specific references to clubs or organizations

    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
    +0.24
    1.1%
    326
    +0.12
    0.5%
    211
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.24
    0.09
    211
    +0.12
    -0.00
    243
    +0.11
    0.07
    Negative Logits
     IMAGES
    -0.81
    å¦
    -0.77
    Accessory
    -0.76
    SourceFile
    -0.73
     Marketable
    -0.72
    inventoryQuantity
    -0.71
    NESS
    -0.71
     defic
    -0.69
    é¾į
    -0.67
    ãģĹ
    -0.66
    POSITIVE LOGITS
    bing
    1.29
    bable
    1.11
    bers
    1.05
    bish
    0.95
    bie
    0.94
    bies
    0.90
    bed
    0.90
     Club
    0.88
     membership
    0.88
    houses
    0.88
    Activations Density 5.477%

    No Known Activations