© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 8869
    Prev
    Next
    INDEX
    Explanations

    references to licenses

    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
    307
    +0.19
    1.1%
    244
    +0.15
    0.8%
    78
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    244
    +0.19
    0.02
    431
    +0.15
    0.01
    75
    +0.12
    0.01
    Negative Logits
    ly
    -1.63
     enough
    -1.62
    lessly
    -1.54
    ized
    -1.46
    ially
    -1.45
    enough
    -1.42
    ally
    -1.42
    less
    -1.41
    izable
    -1.40
    iasis
    -1.39
    POSITIVE LOGITS
    ģ
    2.81
    ľ
    2.49
    ¶
    2.48
    Ĩ
    2.48
    £
    2.44
    ↵↵
    2.39
    ↵
    2.39
    <|outofrange|>
    2.39
    2.39
    <|outofrange|>
    2.39
    Activations Density 0.043%

    No Known Activations