© 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. 8128
    Prev
    Next
    INDEX
    Explanations

    email addresses and contact information

    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
    697
    +0.20
    0.6%
    434
    +0.20
    0.6%
    238
    +0.19
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.20
    0.11
    266
    +0.20
    0.14
    284
    +0.19
    0.09
    Negative Logits
     Scheme
    -1.33
     Ninth
    -1.23
     Kut
    -1.23
     Conclusion
    -1.17
     Index
    -1.16
    )=(
    -1.15
     Reconstruction
    -1.14
     Brach
    -1.13
     Eighth
    -1.12
    Fit
    -1.11
    POSITIVE LOGITS
    @
    1.49
    olson
    1.42
    info
    1.39
    iverpool
    1.37
    tv
    1.36
    mc
    1.33
    podcast
    1.30
    _
    1.27
    yond
    1.27
    anc
    1.26
    Activations Density 3.509%

    No Known Activations