© 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. 25427
    Prev
    Next
    INDEX
    Explanations

    references to particular songs and their titles

    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
    198
    +0.12
    0.7%
    387
    +0.12
    0.7%
    161
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.12
    0.08
    34
    +0.12
    0.12
    313
    +0.11
    0.10
    Negative Logits
    Ĺ
    -2.32
    ¯
    -2.12
    ¸
    -1.89
    ¡
    -1.85
    ·
    -1.84
    »
    -1.84
    ²
    -1.83
    µ
    -1.83
    ª
    -1.82
    °
    -1.81
    POSITIVE LOGITS
    !,
    1.94
    !”
    1.94
    etica
    1.86
    ’
    1.74
    break
    1.72
    âĦ¢
    1.67
    breaker
    1.67
    !
    1.66
    ?,
    1.65
    scape
    1.65
    Activations Density 1.927%

    No Known Activations