Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 27015
    Prev
    Next
    INDEX
    Explanations

    references to regional contexts or entities

    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
    +0.29
    1.7%
    30
    +0.17
    1.0%
    119
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.29
    0.03
    503
    +0.17
    0.02
    119
    +0.13
    0.01
    Negative Logits
     true
    -1.60
    &&
    -1.54
     rigorous
    -1.47
    attr
    -1.45
    rav
    -1.41
    olean
    -1.39
    grily
    -1.38
     hav
    -1.37
     True
    -1.36
     volatile
    -1.36
    POSITIVE LOGITS
    ised
    2.27
    ize
    2.23
    izing
    1.97
    ising
    1.94
    izer
    1.86
    ized
    1.84
    izes
    1.79
    ise
    1.74
    isation
    1.72
    isations
    1.71
    Activations Density 0.057%

    No Known Activations