© 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 EvalsExportsAPI 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. 12429
    Prev
    Next
    INDEX
    Explanations

    errors or issues in text, such as a mistake or malfunction

    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
    84
    +0.21
    0.7%
    332
    +0.15
    0.5%
    474
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.21
    0.12
    679
    +0.15
    0.10
    6
    +0.14
    0.08
    Negative Logits
     lashes
    -1.22
    ecd
    -1.02
    Hunt
    -1.01
    iaries
    -0.98
    ynes
    -0.96
     apostles
    -0.96
    theless
    -0.94
    aunts
    -0.93
    nels
    -0.93
    fights
    -0.91
    POSITIVE LOGITS
     Invalid
    1.25
     wrong
    1.02
    cgi
    1.02
     missing
    0.99
     Missing
    0.99
     %%
    0.95
     happening
    0.94
     improper
    0.94
     Please
    0.93
     incorrect
    0.93
    Activations Density 1.967%

    No Known Activations