© 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. 11490
    Prev
    Next
    INDEX
    Explanations

    structured data representations, particularly in the context of programming or coding 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
    78
    +0.34
    2.3%
    9
    +0.23
    1.5%
    397
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.34
    0.18
    78
    +0.23
    0.05
    397
    +0.14
    0.15
    Negative Logits
    .“
    -1.30
    :-
    -1.29
    .\[[@
    -1.24
    heres
    -1.23
    aries
    -1.23
     trained
    -1.19
    )<
    -1.17
    :
    -1.17
     wrapper
    -1.16
     â
    -1.15
    POSITIVE LOGITS
    Īĺ
    4.35
    <|outofrange|>
    4.26
    4.26
    ↵
    4.26
    ↵↵↵
    4.26
    ↵
    4.26
    <|outofrange|>
    4.26
    4.26
                ↵
    4.26
    <|outofrange|>
    4.26
    Activations Density 1.591%

    No Known Activations