© 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. 27491
    Prev
    Next
    INDEX
    Explanations

    HTML table row tags

    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
    404
    +0.15
    0.8%
    193
    +0.12
    0.7%
    383
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.15
    0.02
    371
    +0.12
    0.02
    77
    +0.11
    0.01
    Negative Logits
    ľĵ
    -2.19
    -2.15
    -2.15
    ↵↵
    -2.15
    ↵
    -2.15
    -2.15
    ↵
    -2.15
    -2.15
    ↵
    -2.15
              ↵
    -2.15
    POSITIVE LOGITS
    ^](#
    1.76
     BGCOLOR
    1.70
    AIN
    1.59
    aman
    1.54
    anges
    1.45
    ANS
    1.44
    neck
    1.43
    OUBLE
    1.42
    iant
    1.42
    UCK
    1.40
    Activations Density 0.077%

    No Known Activations