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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 40651
    Prev
    Next
    INDEX
    Explanations

    text related to computer programming, including concepts like variables, hex color codes, coding syntax, and programming functions

    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
    +0.14
    0.7%
    218
    +0.14
    0.6%
    158
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    570
    +0.14
    -0.00
    738
    +0.14
    0.06
    652
    +0.12
    0.07
    Negative Logits
    DON
    -0.80
    SEE
    -0.67
     Canad
    -0.66
     Feder
    -0.66
     Presidents
    -0.65
     misunder
    -0.63
     SEN
    -0.62
    Surv
    -0.61
     AUTHOR
    -0.61
    ordering
    -0.61
    POSITIVE LOGITS
    raphics
    0.82
     float
    0.78
    peg
    0.78
    ãĥ¼ãĥĨ
    0.77
    ãĤ¨ãĥ«
    0.76
    dylib
    0.76
     glass
    0.74
    ixture
    0.74
    olor
    0.74
     plasma
    0.73
    Activations Density 12.859%

    No Known Activations