© 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. 9891
    Prev
    Next
    INDEX
    Explanations

    database-related commands and table operations

    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
    +0.16
    0.9%
    253
    +0.14
    0.8%
    357
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    253
    +0.16
    0.05
    78
    +0.14
    0.00
    357
    +0.11
    0.04
    Negative Logits
    enta
    -2.04
    ially
    -1.89
    ials
    -1.80
    inities
    -1.74
    inity
    -1.64
    ographers
    -1.60
    zzles
    -1.59
    brow
    -1.59
    bia
    -1.58
    otec
    -1.56
    POSITIVE LOGITS
    «
    4.25
    ł
    4.21
    ±
    4.04
    ¬
    4.03
    ·
    4.03
    ģ
    3.96
    °
    3.93
    Ł
    3.85
    ľĵ
    3.81
    Ĥ¬
    3.78
    Activations Density 0.213%

    No Known Activations