© 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. 9932
    Prev
    Next
    INDEX
    Explanations

    references to early stages or onset of conditions or events

    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
    260
    +0.11
    0.6%
    223
    +0.10
    0.6%
    414
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.11
    0.03
    414
    +0.10
    0.03
    15
    +0.10
    0.03
    Negative Logits
    porter
    -1.68
    pere
    -1.63
    blogger
    -1.61
    soever
    -1.58
    suppl
    -1.57
    atility
    -1.49
    tte
    -1.48
    writer
    -1.47
    hir
    -1.47
    Getty
    -1.47
    POSITIVE LOGITS
    £
    2.83
     stages
    2.50
    ĸ
    2.46
     adop
    2.39
    »
    2.38
    Ĩ
    2.31
    ¢
    2.30
    ĭ
    2.29
    ł
    2.25
    ī
    2.24
    Activations Density 0.086%

    No Known Activations