© 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. 4-RES-SM
    11. 10099
    Prev
    Next
    INDEX
    Explanations

    distinctive names or proper nouns associated with individuals

    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
    21
    +0.20
    1.1%
    269
    +0.14
    0.8%
    318
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    318
    +0.20
    0.10
    410
    +0.14
    0.09
    179
    +0.14
    0.10
    Negative Logits
    -6.19
    ↵  ↵
    -6.19
    ↵
    -6.19
    -6.19
    ↵
    -6.19
    ↵↵
    -6.19
    <|padding|>
    -6.19
    -6.19
    č↵č↵
    -6.19
    <|outofrange|>
    -6.19
    POSITIVE LOGITS
     Jr
    3.01
    sson
    2.33
    udeau
    2.29
    ère
    2.25
    æ°ı
    2.24
     Esq
    2.19
    ovich
    2.18
    opoulos
    2.18
    icz
    2.16
    ovic
    2.16
    Activations Density 0.481%

    No Known Activations