© 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. 13907
    Prev
    Next
    INDEX
    Explanations

    terms related to accuracy and precision in reporting or analysis

    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
    +0.17
    1.0%
    255
    +0.11
    0.6%
    120
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.17
    0.02
    351
    +0.11
    0.06
    9
    +0.10
    0.04
    Negative Logits
    helf
    -1.69
    mania
    -1.56
    manship
    -1.54
    osen
    -1.49
    hop
    -1.48
    ringer
    -1.47
    izon
    -1.41
    hift
    -1.36
    room
    -1.35
    undry
    -1.34
    POSITIVE LOGITS
    acies
    3.07
    acy
    2.65
    ately
    2.35
    ality
    2.00
    º
    1.93
    İ
    1.91
    Ĭ
    1.87
    ¾
    1.86
    ij
    1.86
    ¦
    1.81
    Activations Density 0.734%

    No Known Activations