© 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. 1-RES-SM
    11. 27127
    Prev
    Next
    INDEX
    Explanations

    instances of the word "blow" in various contexts

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    452
    +0.13
    0.8%
    164
    +0.12
    0.7%
    490
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    429
    +0.13
    0.02
    452
    +0.12
    0.02
    164
    +0.12
    0.02
    Negative Logits
    ľĵ
    -1.92
    Į
    -1.79
    ©
    -1.70
    ¹
    -1.70
    ção
    -1.68
    ¡
    -1.66
    ¦
    -1.66
    Ļ
    -1.66
    URAL
    -1.61
    Ł
    -1.56
    POSITIVE LOGITS
    ups
    2.23
    cases
    2.07
    iston
    1.76
    wire
    1.64
    bands
    1.63
    gren
    1.62
    itzer
    1.60
    job
    1.58
     Redistributions
    1.57
    case
    1.57
    Activations Density 0.097%

    No Known Activations