© 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. Residuals
    9. 1-RES-SM
    11. 28336
    Prev
    Next
    INDEX
    Explanations

    references to file names or file-related operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    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
    217
    +0.16
    0.9%
    156
    +0.13
    0.7%
    87
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    217
    +0.16
    0.02
    379
    +0.13
    0.03
    87
    +0.13
    0.02
    Negative Logits
    ·
    -2.41
    ·¸
    -2.23
    Ł
    -2.10
    ´
    -2.06
    ½
    -2.04
    ķ
    -1.98
    ³
    -1.95
    Ĭ
    -1.81
    ²
    -1.77
    ¸
    -1.70
    POSITIVE LOGITS
    icum
    1.88
    icus
    1.72
    osse
    1.63
    ensively
    1.61
    lict
    1.59
    lected
    1.58
    iano
    1.55
    VII
    1.54
    illery
    1.52
    idone
    1.52
    Activations Density 0.229%

    No Known Activations