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. 27002
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases or constructs starting with "on"

    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
    478
    +0.18
    1.0%
    69
    +0.18
    1.0%
    47
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.18
    0.11
    328
    +0.18
    0.07
    243
    +0.14
    0.06
    Negative Logits
     hell
    -1.67
    wise
    -1.63
     pockets
    -1.58
    ishly
    -1.53
    esh
    -1.49
     betting
    -1.41
    oud
    -1.40
     logo
    -1.37
     Pradesh
    -1.37
    urally
    -1.35
    POSITIVE LOGITS
    ĻĤ
    4.98
    Ļª
    4.48
    «
    4.22
    ĸ´
    4.21
    ¿½
    4.17
    ĨĴ
    4.14
    ı
    4.00
    Ĭ
    3.95
    Īĺ
    3.90
    ĥ
    3.86
    Activations Density 0.284%

    No Known Activations