© 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. 45922
    Prev
    Next
    INDEX
    Explanations

    names containing the specific sequence "uch"

    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
    288
    +0.12
    0.6%
    284
    +0.11
    0.5%
    151
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    406
    +0.12
    0.07
    284
    +0.11
    0.07
    701
    +0.10
    0.04
    Negative Logits
     eaves
    -0.68
    mith
    -0.63
     contrace
    -0.63
    uckland
    -0.62
    ©¶æ
    -0.62
     primed
    -0.61
    wcs
    -0.61
    xtap
    -0.60
     Wass
    -0.60
     diminishing
    -0.59
    POSITIVE LOGITS
    icago
    1.07
    anan
    0.89
    arist
    0.82
    inas
    0.76
    atan
    0.74
    ta
    0.72
    onne
    0.72
    ino
    0.70
    iban
    0.69
    atile
    0.68
    Activations Density 4.641%

    No Known Activations