© 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. 13444
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with accountability and societal responsibility

    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
    15
    +0.15
    0.8%
    198
    +0.13
    0.7%
    127
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.15
    0.16
    15
    +0.13
    0.15
    127
    +0.13
    0.13
    Negative Logits
    ĻĤ
    -5.49
    ĨĴ
    -5.30
    ı
    -5.21
    Ĵ
    -5.11
    -5.06
     ↵
    -5.06
    ↵
    -5.06
    -5.06
    ↵
    -5.06
    č↵
    -5.06
    POSITIVE LOGITS
     obstacle
    1.70
    points
    1.48
    standing
    1.46
     tracer
    1.45
     airborne
    1.43
     extrinsic
    1.42
     objective
    1.39
     hypotheses
    1.39
    holder
    1.35
    glass
    1.33
    Activations Density 2.200%

    No Known Activations