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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 26845
    Prev
    Next
    INDEX
    Explanations

    numeric patterns or symbols indicating data structure elements

    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
    39
    +0.13
    0.8%
    488
    +0.13
    0.7%
    497
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    451
    +0.13
    0.01
    39
    +0.13
    0.02
    155
    +0.12
    0.01
    Negative Logits
     spot
    -1.61
     marked
    -1.50
    abouts
    -1.47
    amen
    -1.44
     crashed
    -1.43
    ty
    -1.41
    ctic
    -1.38
    ila
    -1.36
    ids
    -1.35
     park
    -1.34
    POSITIVE LOGITS
    !/
    1.53
     novels
    1.50
     fiction
    1.47
    resis
    1.44
     journalism
    1.43
    ...]
    1.43
     ourselves
    1.41
    elif
    1.39
     prose
    1.39
     Letter
    1.38
    Activations Density 0.056%

    No Known Activations