© 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. 33304
    Prev
    Next
    INDEX
    Explanations

    international characters

    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
    526
    +0.17
    0.7%
    679
    +0.11
    0.5%
    35
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.16
    288
    +0.11
    0.15
    555
    +0.11
    0.07
    Negative Logits
     optic
    -0.69
    20439
    -0.68
     Nun
    -0.67
    theless
    -0.65
    BSD
    -0.65
     Suff
    -0.64
    meal
    -0.64
    ãĤ¡
    -0.64
    itably
    -0.64
    phia
    -0.63
    POSITIVE LOGITS
    arro
    1.05
    Ģ
    1.01
    urations
    0.91
    acs
    0.89
    ota
    0.87
    eters
    0.86
    ating
    0.85
    anes
    0.84
    ´
    0.83
    ingle
    0.81
    Activations Density 4.157%

    No Known Activations