© 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. 33718
    Prev
    Next
    INDEX
    Explanations

    words related to computer science and technology

    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
    373
    +0.18
    1.1%
    68
    +0.08
    0.5%
    113
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.18
    -0.08
    659
    +0.08
    0.10
    326
    +0.07
    0.12
    Negative Logits
    tein
    -0.60
    lain
    -0.58
    cair
    -0.56
    gling
    -0.53
    baugh
    -0.52
    edged
    -0.51
     Ivory
    -0.50
     þ
    -0.48
    sein
    -0.48
    aux
    -0.48
    POSITIVE LOGITS
    Wiki
    0.66
    Politics
    0.66
    Radio
    0.64
    Fly
    0.62
    News
    0.61
    Doc
    0.60
    Talk
    0.59
    Studio
    0.59
    Maps
    0.58
    Scan
    0.58
    Activations Density 2.168%

    No Known Activations