© 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. 14929
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and quantitative details

    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
    156
    +0.16
    0.9%
    271
    +0.14
    0.7%
    307
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    219
    +0.16
    0.10
    61
    +0.14
    0.08
    420
    +0.12
    0.08
    Negative Logits
    .";
    -2.98
    .''
    -2.65
    ."_
    -2.63
    **_
    -2.61
    ";
    -2.53
    .""
    -2.53
    .'"
    -2.33
    ';
    -2.19
    «
    -2.18
    `.
    -2.17
    POSITIVE LOGITS
    )
    4.63
    ),
    4.19
    ):
    4.09
    )"
    3.83
    )."
    3.73
    )',
    3.68
    )",
    3.66
    )'
    3.60
    )&
    3.55
    !)
    3.55
    Activations Density 1.422%

    No Known Activations