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. 2-RES-SM
    6. 29251
    Prev
    Next
    INDEX
    Explanations

    forms of the verb 'use'

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    274
    +0.16
    0.9%
    478
    +0.14
    0.8%
    282
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    274
    +0.16
    0.06
    282
    +0.14
    0.05
    108
    +0.13
    0.05
    Negative Logits
    vier
    -1.51
    hof
    -1.46
    omitempty
    -1.44
    uality
    -1.39
     Managing
    -1.37
    iedad
    -1.35
    ume
    -1.35
     beginnings
    -1.33
     contributor
    -1.33
    ios
    -1.33
    POSITIVE LOGITS
     alone
    1.83
     them
    1.63
    icides
    1.63
     conventional
    1.53
     other
    1.53
    amid
    1.50
     specially
    1.48
     primarily
    1.47
     mostly
    1.47
    valued
    1.45
    Activations Density 0.202%

    No Known Activations