© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 33222
    Prev
    Next
    INDEX
    Explanations

    names that start with "Ak" and related names or parts of names

    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
    +0.16
    0.7%
    549
    +0.14
    0.6%
    755
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.16
    0.07
    549
    +0.14
    0.06
    655
    +0.12
    0.07
    Negative Logits
    enegger
    -0.75
    iculty
    -0.70
     Hurricanes
    -0.67
    åĤ
    -0.65
     Founders
    -0.64
     Quadro
    -0.63
     Reaper
    -0.63
    ACE
    -0.62
    IFIED
    -0.62
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.61
    POSITIVE LOGITS
    atsuki
    1.13
    ule
    1.03
    ansas
    0.98
    uri
    0.96
    umar
    0.95
    uin
    0.95
    htar
    0.93
    rue
    0.93
    adem
    0.92
    uma
    0.90
    Activations Density 6.277%

    No Known Activations