© 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. 45778
    Prev
    Next
    INDEX
    Explanations

    words related to clothing and attire, particularly focusing on dresses

    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
    +0.17
    0.7%
    288
    +0.13
    0.5%
    526
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.17
    0.17
    325
    +0.13
    0.08
    326
    +0.12
    0.17
    Negative Logits
    ntil
    -0.97
    ocalyptic
    -0.86
    emonic
    -0.79
    untu
    -0.78
    è¦ļéĨĴ
    -0.77
    ategory
    -0.77
    uilt
    -0.77
    ichael
    -0.75
    rals
    -0.73
    rw
    -0.72
    POSITIVE LOGITS
    maker
    1.16
    glers
    1.06
    makers
    1.06
     rehearsal
    1.01
     gown
    1.01
    bag
    0.95
    cases
    0.94
    ings
    0.92
     shoes
    0.89
    cloth
    0.89
    Activations Density 5.409%

    No Known Activations