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. 27028
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical information

    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
    369
    +0.13
    0.7%
    81
    +0.12
    0.6%
    483
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    81
    +0.13
    0.08
    483
    +0.12
    0.06
    458
    +0.11
    0.04
    Negative Logits
    pires
    -1.62
    ateurs
    -1.54
    iers
    -1.53
    ually
    -1.48
    ainers
    -1.47
     perfection
    -1.46
    abases
    -1.46
    chers
    -1.45
    ovo
    -1.42
     nets
    -1.40
    POSITIVE LOGITS
     Filed
    1.46
     audible
    1.42
     breath
    1.41
    hearing
    1.40
     Hz
    1.37
     kHz
    1.36
     hereto
    1.32
    idenote
    1.32
    Hz
    1.32
    :]
    1.31
    Activations Density 0.482%

    No Known Activations