© 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. 12917
    Prev
    Next
    INDEX
    Explanations

    references to semi-automatic firearms

    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
    +0.20
    1.2%
    306
    +0.17
    1.0%
    466
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    386
    +0.20
    0.01
    218
    +0.17
    0.02
    436
    +0.12
    0.01
    Negative Logits
    swers
    -1.50
    INGS
    -1.44
    Hint
    -1.42
     hereby
    -1.38
     direction
    -1.38
     HREF
    -1.38
    Competing
    -1.37
    Docket
    -1.37
    ese
    -1.33
     APPEALS
    -1.33
    POSITIVE LOGITS
    ¼
    3.00
    »
    2.83
    <|outofrange|>
    2.83
    ↵
    2.83
    ↵
    2.83
    ↵  Âł
    2.83
    ↵
    2.83
    2.83
    <|outofrange|>
    2.83
    <|outofrange|>
    2.83
    Activations Density 0.105%

    No Known Activations