© 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. 9081
    Prev
    Next
    INDEX
    Explanations

    phrases and sentences related to trying to understand or explain a situation or problem

    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
    195
    +0.15
    0.5%
    421
    +0.15
    0.5%
    167
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    421
    +0.15
    0.04
    195
    +0.15
    0.02
    70
    +0.14
    0.04
    Negative Logits
    ibaba
    -1.23
    eatures
    -1.19
    ankind
    -1.07
    etheus
    -1.06
    ription
    -1.02
    reath
    -1.01
    athi
    -0.97
    lain
    -0.97
    ãĥĨãĤ£
    -0.97
    chnology
    -0.94
    POSITIVE LOGITS
    istically
    1.16
     skating
    1.11
     prominently
    1.10
    sonian
    1.05
    ling
    0.91
     out
    0.90
    share
    0.89
    inery
    0.85
    stock
    0.85
    ered
    0.84
    Activations Density 0.562%

    No Known Activations