© 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. 14733
    Prev
    Next
    INDEX
    Explanations

    the word "ever" and its variations

    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
    280
    +0.15
    0.8%
    21
    +0.14
    0.8%
    153
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    201
    +0.15
    0.03
    159
    +0.14
    0.03
    313
    +0.13
    0.02
    Negative Logits
    İ
    -2.08
    <|outofrange|>
    -2.02
            ↵
    -2.02
         ↵
    -2.02
    ↵↵
    -2.02
    -2.02
    ↵
    -2.02
     ↵
    -2.02
    -2.02
    <|outofrange|>
    -2.02
    POSITIVE LOGITS
    lasting
    2.92
    green
    2.77
    thing
    2.25
     since
    2.05
    ont
    1.98
    more
    1.75
    theless
    1.70
    ingly
    1.68
    itt
    1.62
    eland
    1.61
    Activations Density 0.153%

    No Known Activations