© 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 EvalsExportsinterp-engineNEWAPI 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. 36203
    Prev
    Next
    INDEX
    Explanations

    technical/scientific language related to heat transfer and thermodynamics

    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
    +0.20
    1.2%
    528
    +0.10
    0.6%
    393
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.34
    640
    +0.10
    0.29
    375
    +0.10
    0.06
    Negative Logits
    bender
    -0.52
    Beh
    -0.50
     craw
    -0.47
    Theme
    -0.47
    BM
    -0.45
     Lash
    -0.45
    bel
    -0.45
    beh
    -0.45
    Brow
    -0.43
    gow
    -0.42
    POSITIVE LOGITS
     9000
    0.55
     [-
    0.53
     equivalent
    0.51
     \(
    0.50
    amount
    0.50
    apo
    0.50
     minus
    0.49
     [+
    0.49
     nil
    0.49
     ppm
    0.49
    Activations Density 16.349%

    No Known Activations