© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11294
    Prev
    Next
    INDEX
    Explanations

    references to eating and hunger

    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
    115
    +0.15
    0.8%
    56
    +0.13
    0.7%
    156
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.15
    0.01
    115
    +0.13
    0.04
    263
    +0.13
    0.05
    Negative Logits
    Ŀ
    -3.10
    <|outofrange|>
    -2.74
    -2.74
    ↵
    -2.74
     ↵
    -2.74
    -2.74
    ↵
    -2.74
     ↵
    -2.74
    -2.74
    ↵
    -2.74
    POSITIVE LOGITS
     habits
    1.97
     habit
    1.88
    aways
    1.83
     shit
    1.81
    ubottu
    1.75
     away
    1.72
     tons
    1.68
     regularly
    1.68
    abouts
    1.68
    acious
    1.67
    Activations Density 0.479%

    No Known Activations