© 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. 9555
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to software dependencies

    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
    +0.25
    1.4%
    156
    +0.19
    1.1%
    95
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    95
    +0.25
    0.10
    370
    +0.19
    0.12
    252
    +0.12
    0.05
    Negative Logits
    ĥ½
    -2.75
    -2.40
    ↵↵
    -2.40
    <|outofrange|>
    -2.40
    <|outofrange|>
    -2.40
    č↵
    -2.40
    ↵    ↵
    -2.40
    -2.40
    ↵
    -2.40
    <|outofrange|>
    -2.40
    POSITIVE LOGITS
    sdk
    2.22
    cli
    2.20
    lib
    2.09
    LICENSE
    2.07
    ://
    2.04
    bsd
    2.03
    libs
    2.03
    rc
    2.00
    pkg
    1.98
    untime
    1.98
    Activations Density 1.247%

    No Known Activations