© 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. 12970
    Prev
    Next
    INDEX
    Explanations

    metrics and statistical measurements

    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
    122
    +0.16
    0.9%
    6
    +0.13
    0.8%
    186
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    387
    +0.16
    0.14
    6
    +0.13
    0.14
    122
    +0.13
    0.08
    Negative Logits
    "}](#
    -1.57
    arten
    -1.57
     wine
    -1.32
    orta
    -1.31
    cker
    -1.31
     glimpse
    -1.30
    \":
    -1.29
    mmas
    -1.28
    erate
    -1.27
    acial
    -1.26
    POSITIVE LOGITS
    oxford
    1.54
    inent
    1.48
    education
    1.47
    onym
    1.42
     education
    1.39
     Spacewatch
    1.38
     liter
    1.38
     ),
    1.35
    /~
    1.35
    care
    1.29
    Activations Density 7.190%

    No Known Activations