© 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. 33758
    Prev
    Next
    INDEX
    Explanations

    details related to weights and measures

    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
    +0.08
    0.5%
    240
    +0.07
    0.4%
    459
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.08
    0.15
    326
    +0.07
    0.23
    743
    +0.07
    0.04
    Negative Logits
    western
    -0.61
     Chapman
    -0.54
    duction
    -0.51
    utenant
    -0.49
    ogyn
    -0.49
    rosis
    -0.49
    isation
    -0.48
     subp
    -0.48
    comed
    -0.48
     Paradox
    -0.47
    POSITIVE LOGITS
    eki
    0.70
    acity
    0.61
    ages
    0.58
    lies
    0.58
    ible
    0.57
    MENTS
    0.57
    cake
    0.56
    ables
    0.56
    ickr
    0.55
    Merit
    0.54
    Activations Density 9.807%

    No Known Activations