© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 26261
    Prev
    Next
    INDEX
    Explanations

    references to scars and scar-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    148
    +0.14
    0.8%
    2
    +0.12
    0.7%
    343
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.14
    0.01
    303
    +0.12
    0.01
    291
    +0.12
    0.01
    Negative Logits
    ){#
    -1.55
    gmail
    -1.49
    yahoo
    -1.46
    ometh
    -1.40
     Jewish
    -1.39
    rapeut
    -1.36
    elf
    -1.34
    agle
    -1.33
     entire
    -1.33
     invention
    -1.30
    POSITIVE LOGITS
    ceral
    2.09
    ier
    1.80
    witz
    1.74
    ¢
    1.73
    buk
    1.68
    vin
    1.66
    ves
    1.63
    "}](#
    1.59
    ring
    1.55
     [$
    1.53
    Activations Density 0.009%

    No Known Activations