© 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 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. 28838
    Prev
    Next
    INDEX
    Explanations

    references to cyber-related topics and vocabulary

    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
    43
    +0.13
    0.8%
    445
    +0.13
    0.7%
    317
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    445
    +0.13
    0.01
    177
    +0.13
    0.02
    503
    +0.13
    0.02
    Negative Logits
     Caption
    -1.82
    ailing
    -1.68
     descent
    -1.64
     previous
    -1.48
     other
    -1.47
     lack
    -1.44
     mind
    -1.44
     longest
    -1.42
    ails
    -1.41
    izations
    -1.40
    POSITIVE LOGITS
    °
    2.20
    ¤
    1.96
    ł
    1.96
    ģ
    1.95
    Ł
    1.94
    tochrome
    1.94
    Ķ
    1.93
    ²
    1.93
    Ĵ
    1.85
    Ļ
    1.85
    Activations Density 0.157%

    No Known Activations