© 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. 12619
    Prev
    Next
    INDEX
    Explanations

    numerical codes or identifiers within a technical or configuration context

    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
    59
    +0.16
    0.9%
    39
    +0.14
    0.8%
    450
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.16
    0.04
    59
    +0.14
    0.04
    136
    +0.14
    0.00
    Negative Logits
    odynamics
    -1.68
    ±
    -1.67
    ,”
    -1.53
    uities
    -1.46
     ±
    -1.45
    ,'"
    -1.43
    ,--
    -1.38
    ,''
    -1.38
    $),
    -1.38
    ini
    -1.37
    POSITIVE LOGITS
    ¿
    4.12
    ±
    3.82
    ´
    3.80
    °
    3.79
    Ł
    3.65
    ¾
    3.53
    ¶
    3.52
    ¸
    3.49
    ĥ½
    3.48
    ¯
    3.46
    Activations Density 0.455%

    No Known Activations