© 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. 4-RES-SM
    11. 10587
    Prev
    Next
    INDEX
    Explanations

    references to data, categories, or attributes in structured formats

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    425
    +0.13
    0.8%
    137
    +0.12
    0.7%
    462
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.13
    0.03
    130
    +0.12
    0.06
    186
    +0.11
    0.04
    Negative Logits
    £
    -4.13
    ±
    -4.12
    Ĺ
    -4.02
    ĭ
    -3.98
    «
    -3.98
    Ĥ
    -3.96
    ı
    -3.96
    Ŀ
    -3.90
    ¤
    -3.87
    ³
    -3.85
    POSITIVE LOGITS
     and
    3.73
    and
    3.01
     AND
    2.62
    And
    2.29
     or
    2.06
     etc
    2.06
    AND
    2.02
     but
    1.98
     And
    1.95
     &
    1.92
    Activations Density 0.952%

    No Known Activations