© 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. 2-RES-SM
    11. 31549
    Prev
    Next
    INDEX
    Explanations

    patterns and components related to data analysis and testing frameworks

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    423
    +0.17
    1.0%
    12
    +0.16
    0.9%
    183
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.17
    0.09
    237
    +0.16
    0.08
    400
    +0.12
    0.04
    Negative Logits
     sole
    -1.56
     chore
    -1.38
     consec
    -1.37
    ensis
    -1.37
     veto
    -1.36
    oning
    -1.35
    ophil
    -1.35
     Review
    -1.35
    liche
    -1.29
     afferent
    -1.27
    POSITIVE LOGITS
    ocker
    1.75
    ocks
    1.67
    reements
    1.44
    ections
    1.44
     yourself
    1.40
    iations
    1.40
    ICATION
    1.39
    meet
    1.38
     Russia
    1.37
    ieurs
    1.37
    Activations Density 1.535%

    No Known Activations