© 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. 13689
    Prev
    Next
    INDEX
    Explanations

    words related to transfers or movements of data, assets, or control from one entity to another

    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%
    288
    +0.18
    0.8%
    137
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.24
    0.12
    385
    +0.18
    0.13
    330
    +0.14
    0.07
    Negative Logits
    à©
    -0.75
    ãĥĦ
    -0.71
    akening
    -0.67
    194
    -0.66
    Downloadha
    -0.65
    aces
    -0.64
    adal
    -0.64
    FORE
    -0.63
    GE
    -0.63
    GH
    -0.61
    POSITIVE LOGITS
    ring
    0.87
    metry
    0.82
    ster
    0.81
     transfers
    0.74
    able
    0.74
     between
    0.73
     fluids
    0.71
     transfer
    0.71
    brates
    0.71
    itures
    0.70
    Activations Density 11.266%

    No Known Activations