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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11144
    Prev
    Next
    INDEX
    Explanations

    references to specific counties or geographical locations

    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
    503
    +0.15
    0.9%
    397
    +0.14
    0.8%
    34
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    503
    +0.15
    0.04
    34
    +0.14
    0.03
    242
    +0.13
    0.03
    Negative Logits
    ĥ½
    -2.18
    <|outofrange|>
    -2.02
    ↵
    -2.02
    -2.02
    -2.02
    ↵
    -2.02
    ↵  ³³³
    -2.02
    <|outofrange|>
    -2.02
    ↵↵
    -2.02
    -2.02
    POSITIVE LOGITS
     Sheriff
    2.11
    wide
    1.98
     sheriff
    1.88
    ways
    1.87
     Clerk
    1.85
    way
    1.81
    staff
    1.69
    view
    1.67
     Attorney
    1.63
    oyer
    1.60
    Activations Density 0.111%

    No Known Activations