© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10291
    Prev
    Next
    INDEX
    Explanations

    concepts related to quantum physics

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    Neuron Alignment
    Index
    Value
    % of L₁
    578
    +0.23
    0.8%
    271
    +0.15
    0.5%
    649
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.23
    0.11
    578
    +0.15
    0.06
    326
    +0.15
    0.08
    Negative Logits
    iak
    -1.16
    ashington
    -1.10
    HCR
    -1.06
    phia
    -1.02
    ieft
    -0.98
    inav
    -0.96
    retched
    -0.95
    hetto
    -0.93
    ifestyle
    -0.93
    anie
    -0.92
    POSITIVE LOGITS
     physicists
    1.67
     physicist
    1.59
     Collider
    1.36
     physics
    1.35
     particle
    1.31
    ertodd
    1.17
     gravity
    1.16
     particles
    1.13
    agine
    1.13
     Physics
    1.10
    Activations Density 1.396%

    No Known Activations