© 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. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 26155
    Prev
    Next
    INDEX
    Explanations

    references to a specific historical event or individual

    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
    76
    +0.13
    0.7%
    111
    +0.12
    0.7%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.13
    0.02
    174
    +0.12
    0.02
    317
    +0.12
    0.01
    Negative Logits
    onyl
    -1.68
    atur
    -1.68
    night
    -1.57
     ?
    -1.53
    OLOR
    -1.52
    uated
    -1.49
    apper
    -1.44
    Rear
    -1.43
    edin
    -1.42
     happening
    -1.41
    POSITIVE LOGITS
    §
    3.44
    °
    3.30
    ¯
    3.29
    ±
    3.12
    ¥
    3.12
    «
    3.11
    Ľ
    3.01
    ¤
    2.94
    ·
    2.93
    Ĵ
    2.93
    Activations Density 0.119%

    No Known Activations