© 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. 1-RES-SM
    11. 29447
    Prev
    Next
    INDEX
    Explanations

    references to collaboration or involvement in activities

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    20
    +0.13
    0.7%
    502
    +0.13
    0.7%
    53
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.13
    0.04
    502
    +0.13
    0.04
    372
    +0.12
    0.04
    Negative Logits
    ¢
    -2.44
    ¥
    -2.28
    ®
    -2.28
    »¿
    -2.23
    Ģ
    -2.18
    ļ
    -2.06
    »
    -2.06
    ±
    -2.05
    Ń
    -2.00
    Ĵ
    -1.98
    POSITIVE LOGITS
    isans
    2.20
    ridges
    2.02
    aking
    2.00
    ridge
    1.98
    aker
    1.57
    aken
    1.55
    ners
    1.48
    agem
    1.45
    omorphic
    1.44
    igue
    1.42
    Activations Density 0.059%

    No Known Activations