© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7155
    Prev
    Next
    INDEX
    Explanations

    specific names or terms related to mathematicians and artists

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    649
    +0.17
    0.5%
    659
    +0.16
    0.5%
    116
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.17
    0.06
    700
    +0.16
    0.05
    284
    +0.15
    0.05
    Negative Logits
     Scots
    -1.31
    naissance
    -1.18
     foss
    -1.03
    croft
    -1.02
     satell
    -1.02
     Palestin
    -0.99
    ó
    -0.98
     ransom
    -0.96
    ndra
    -0.95
     behavi
    -0.94
    POSITIVE LOGITS
    ombie
    2.33
    ombies
    1.81
    ijn
    1.57
    hao
    1.56
    ebra
    1.56
    ymes
    1.53
    enegger
    1.49
    oning
    1.47
    ealous
    1.41
    alez
    1.41
    Activations Density 0.686%

    No Known Activations