© 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. 8047
    Prev
    Next
    INDEX
    Explanations

    instances where someone mentions having never experienced or witnessed something before

    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
    718
    +0.14
    0.5%
    398
    +0.14
    0.5%
    404
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    579
    +0.14
    0.06
    398
    +0.14
    0.04
    718
    +0.14
    0.05
    Negative Logits
    æ°
    -0.88
    lr
    -0.88
    hod
    -0.88
    Products
    -0.87
    cp
    -0.86
    SG
    -0.86
    onto
    -0.85
    DF
    -0.84
    Copy
    -0.84
     Reports
    -0.81
    POSITIVE LOGITS
     been
    1.39
    been
    1.34
     existed
    1.16
    theless
    1.15
     tasted
    1.11
     lived
    1.07
     gotten
    1.04
     heard
    1.04
     dreamed
    1.04
     Been
    1.03
    Activations Density 0.349%

    No Known Activations