© 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. 8439
    Prev
    Next
    INDEX
    Explanations

    mentions of saving or preserving something, such as lives, money, or the environment

    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
    402
    +0.18
    0.6%
    288
    +0.15
    0.5%
    57
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.18
    0.04
    57
    +0.15
    0.04
    405
    +0.15
    0.05
    Negative Logits
    naire
    -1.11
    Else
    -1.06
     sclerosis
    -0.88
    issance
    -0.88
    interstitial
    -0.87
     elder
    -0.87
    ple
    -0.87
    RY
    -0.86
    FG
    -0.85
    essee
    -0.84
    POSITIVE LOGITS
    Save
    1.25
     Saving
    1.07
    saving
    1.06
     Save
    1.01
     luc
    0.97
     Sanctuary
    0.96
     Savings
    0.95
    ift
    0.94
     save
    0.94
     saving
    0.92
    Activations Density 0.964%

    No Known Activations