© 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. 45850
    Prev
    Next
    INDEX
    Explanations

    terms related to wholesale prices and trade

    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
    240
    +0.14
    0.6%
    459
    +0.14
    0.6%
    198
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.21
    459
    +0.14
    0.13
    326
    +0.11
    0.21
    Negative Logits
    pmwiki
    -0.90
    aque
    -0.82
     MacArthur
    -0.80
    adian
    -0.79
    ularity
    -0.75
    uyomi
    -0.74
    ril
    -0.73
    rises
    -0.73
    bable
    -0.72
    pas
    -0.71
    POSITIVE LOGITS
    Ò
    1.02
     wholes
    0.95
    xual
    0.91
     distribut
    0.86
    ocial
    0.83
    soDeliveryDate
    0.80
    ODUCT
    0.79
     wholesale
    0.76
    externalActionCode
    0.74
    aler
    0.72
    Activations Density 7.847%

    No Known Activations