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. 26720
    Prev
    Next
    INDEX
    Explanations

    references to excessive quantities or the concept of "over."

    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
    282
    +0.17
    1.0%
    307
    +0.14
    0.8%
    362
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.17
    0.07
    307
    +0.14
    0.06
    20
    +0.12
    0.05
    Negative Logits
    neum
    -1.73
     eye
    -1.60
    eless
    -1.59
    aldehyde
    -1.59
    OUS
    -1.58
     above
    -1.58
    URE
    -1.58
     bladder
    -1.50
    illar
    -1.49
    neys
    -1.47
    POSITIVE LOGITS
    loaded
    2.26
    came
    2.12
    arching
    1.83
    wrote
    1.79
    powered
    1.70
    throws
    1.69
    saw
    1.67
    cuts
    1.61
    ked
    1.60
    heard
    1.60
    Activations Density 0.106%

    No Known Activations