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. 27024
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and 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
    26
    +0.14
    0.8%
    37
    +0.13
    0.7%
    193
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.14
    0.04
    17
    +0.13
    0.01
    193
    +0.12
    0.04
    Negative Logits
     exhibits
    -1.75
    zel
    -1.48
     surrounds
    -1.45
    dez
    -1.44
    mos
    -1.43
     estimate
    -1.42
     senses
    -1.41
     exhibit
    -1.39
    igu
    -1.37
     hydrodynamic
    -1.36
    POSITIVE LOGITS
     cmd
    1.90
     defeating
    1.61
    uit
    1.55
    microsoft
    1.55
    begin
    1.54
     Equal
    1.52
    ctrine
    1.52
    hline
    1.51
     False
    1.48
    ollywood
    1.48
    Activations Density 0.377%

    No Known Activations