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. 27039
    Prev
    Next
    INDEX
    Explanations

    technical or programming-related syntactical structures

    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
    150
    +0.12
    0.7%
    369
    +0.11
    0.6%
    474
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.12
    0.07
    150
    +0.11
    0.09
    16
    +0.11
    0.06
    Negative Logits
     itself
    -1.80
    UES
    -1.71
    uncher
    -1.64
     later
    -1.64
     reasons
    -1.54
     myself
    -1.52
    gue
    -1.49
    ubicin
    -1.48
    "...
    -1.46
     europea
    -1.45
    POSITIVE LOGITS
    agen
    1.60
     $('
    1.51
    equal
    1.45
    imension
    1.43
    lich
    1.42
    emph
    1.39
    '>
    1.36
     $('.
    1.34
    grass
    1.33
    ently
    1.30
    Activations Density 1.879%

    No Known Activations