© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1801
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific research and historical events, with particular interest in specific dates and technical processes

    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
    274
    +0.17
    0.7%
    444
    +0.14
    0.6%
    31
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.20
    288
    +0.14
    0.22
    232
    +0.13
    0.10
    Negative Logits
    iago
    -1.14
    uring
    -0.98
    orius
    -0.94
    elman
    -0.84
    omy
    -0.82
    omal
    -0.82
    iciary
    -0.81
    urally
    -0.81
    estation
    -0.80
    notation
    -0.80
    POSITIVE LOGITS
    nd
    0.95
    nces
    0.89
     Scotia
    0.87
    isky
    0.79
    ength
    0.79
     Rebellion
    0.78
     Nights
    0.73
     Cats
    0.69
    itable
    0.69
     Cros
    0.69
    Activations Density 5.433%

    No Known Activations