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. 27037
    Prev
    Next
    INDEX
    Explanations

    instances of the word "out."

    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
    209
    +0.13
    0.7%
    125
    +0.13
    0.7%
    382
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    209
    +0.13
    0.06
    125
    +0.13
    0.04
    382
    +0.11
    0.05
    Negative Logits
    rends
    -1.57
    ;</
    -1.52
     BGCOLOR
    -1.51
     magnitude
    -1.48
    >{
    -1.42
    blockList
    -1.42
    chron
    -1.39
    acity
    -1.35
    athered
    -1.33
     finger
    -1.31
    POSITIVE LOGITS
    ermost
    2.01
    perform
    1.86
    lining
    1.81
    haul
    1.50
    lying
    1.50
    tte
    1.49
    patients
    1.49
     candidate
    1.48
    spoken
    1.47
    cry
    1.47
    Activations Density 0.136%

    No Known Activations