© 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. 13492
    Prev
    Next
    INDEX
    Explanations

    references to categories or groups of items or concepts

    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
    156
    +0.21
    1.2%
    137
    +0.11
    0.7%
    130
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    204
    +0.21
    0.04
    130
    +0.11
    0.05
    125
    +0.11
    0.05
    Negative Logits
    ¯
    -2.24
    ½
    -2.08
    creas
    -2.04
    ¶
    -1.97
    º
    -1.87
    fecture
    -1.84
    ĭ
    -1.84
    ение
    -1.75
    ģ
    -1.73
    ·¸
    -1.73
    POSITIVE LOGITS
     kinds
    2.75
     sorts
    2.54
     types
    2.30
     guys
    2.18
     latter
    2.17
     things
    2.11
     are
    2.07
     figures
    2.04
     factors
    2.02
     examples
    1.99
    Activations Density 0.207%

    No Known Activations