© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 11554
    Prev
    Next
    INDEX
    Explanations

    terminology related to programming and software development

    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
    +0.24
    1.5%
    21
    +0.18
    1.2%
    9
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    487
    +0.24
    0.04
    141
    +0.18
    0.05
    273
    +0.14
    0.03
    Negative Logits
    .
    -1.46
    ('',
    -1.37
    umab
    -1.31
    ipore
    -1.26
    ense
    -1.25
    /
    -1.23
    abilities
    -1.23
     parl
    -1.23
    ENTS
    -1.20
    fecture
    -1.20
    POSITIVE LOGITS
     */
    2.96
    »
    2.76
    «
    2.49
    ·
    2.41
    Ĩ
    2.40
    ĵ
    2.31
    Ļ
    2.25
     *
    2.25
    ¼
    2.21
    ¿½
    2.21
    Activations Density 0.204%

    No Known Activations