© 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. 1309
    Prev
    Next
    INDEX
    Explanations

    instances where there is anticipation of an event or action happening in the future

    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
    393
    +0.20
    0.7%
    228
    +0.14
    0.5%
    551
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.20
    0.09
    283
    +0.14
    0.03
    172
    +0.12
    0.05
    Negative Logits
    DAQ
    -0.88
     ç¥ŀ
    -0.85
    arag
    -0.85
    ãĥ¡
    -0.84
    intosh
    -0.84
    ãĤ´ãĥ³
    -0.84
     Exodus
    -0.83
     hijab
    -0.83
    ãĤ´
    -0.82
    \\\\\\\\
    -0.82
    POSITIVE LOGITS
     maxim
    0.94
     Means
    0.90
     youngsters
    0.90
     they
    0.88
    ividual
    0.86
    afort
    0.85
    pload
    0.85
    ndra
    0.85
     sim
    0.85
     whoever
    0.84
    Activations Density 1.603%

    No Known Activations