© 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. 13624
    Prev
    Next
    INDEX
    Explanations

    words indicating unworthiness or a lack of value

    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
    279
    +0.13
    0.8%
    276
    +0.13
    0.7%
    148
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.13
    0.04
    148
    +0.13
    0.02
    276
    +0.12
    0.04
    Negative Logits
    s
    -2.98
    e
    -2.61
    a
    -2.45
    eer
    -2.09
    er
    -1.91
    aq
    -1.74
    i
    -1.68
    ei
    -1.67
    añ
    -1.64
    eon
    -1.58
    POSITIVE LOGITS
    orthern
    2.41
    vironment
    2.30
    ĩ
    2.29
    aturally
    2.17
    ovember
    2.14
    umpy
    2.10
    ®
    2.02
    vidia
    2.00
    inja
    1.99
    apshot
    1.96
    Activations Density 0.129%

    No Known Activations