© 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. 298
    Prev
    Next
    INDEX
    Explanations

    dates and technical instructions related to building a specific type of software/os/image

    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
    444
    +0.14
    0.5%
    499
    +0.12
    0.5%
    721
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.08
    288
    +0.12
    0.08
    464
    +0.12
    0.05
    Negative Logits
    istani
    -1.14
    atform
    -1.05
    heses
    -0.94
    swer
    -0.93
    ivity
    -0.92
    ynamic
    -0.91
    hammad
    -0.88
    TPPStreamerBot
    -0.87
    roma
    -0.85
    raph
    -0.84
    POSITIVE LOGITS
    ographed
    1.20
    mons
    1.06
    ously
    0.95
    ea
    0.90
    ograph
    0.87
    endment
    0.86
    eer
    0.83
    ira
    0.83
    ierre
    0.83
    eering
    0.82
    Activations Density 0.975%

    No Known Activations