© 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. 1-RES-SM
    11. 25171
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to biological activation processes

    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
    156
    +0.17
    1.0%
    376
    +0.14
    0.8%
    93
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.17
    0.37
    156
    +0.14
    0.21
    428
    +0.13
    0.29
    Negative Logits
    oving
    -1.62
    vel
    -1.61
    reich
    -1.54
    agin
    -1.53
    river
    -1.49
    vy
    -1.47
    »¿
    -1.46
    lotte
    -1.46
    urther
    -1.45
    deal
    -1.42
    POSITIVE LOGITS
    ivated
    1.73
     envelope
    1.68
    arily
    1.62
     factors
    1.55
    ivation
    1.53
     thanks
    1.53
     event
    1.50
     modes
    1.49
     mode
    1.48
     pulsed
    1.47
    Activations Density 1.061%

    No Known Activations