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. 26718
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "of" in various contexts

    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
    356
    +0.13
    0.7%
    161
    +0.12
    0.7%
    163
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    295
    +0.13
    0.06
    161
    +0.12
    0.06
    452
    +0.12
    0.07
    Negative Logits
     costs
    -1.51
    arman
    -1.43
     soundtrack
    -1.42
    arily
    -1.41
     preced
    -1.40
     priority
    -1.35
     canal
    -1.34
     orders
    -1.34
     drummer
    -1.33
     Heisenberg
    -1.32
    POSITIVE LOGITS
    ĻĤ
    2.42
    Ļ
    2.32
    ĨĴ
    2.29
    ¿½
    2.24
    ľĵ
    2.19
    ĸ
    2.13
    £
    2.12
    ļ
    2.09
    Ń
    2.07
    į
    2.07
    Activations Density 0.673%

    No Known Activations