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. 29237
    Prev
    Next
    INDEX
    Explanations

    repetitions of the word "you."

    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
    410
    +0.16
    0.9%
    241
    +0.14
    0.8%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    410
    +0.16
    0.03
    59
    +0.14
    0.02
    477
    +0.12
    0.03
    Negative Logits
    onymous
    -2.10
    ogr
    -1.99
     asleep
    -1.66
    otle
    -1.63
    igraph
    -1.58
    ocal
    -1.55
    emic
    -1.52
    onym
    -1.51
    uric
    -1.50
    ocur
    -1.50
    POSITIVE LOGITS
    ´
    2.22
    ī
    2.11
    Ŀ
    2.08
    illard
    2.07
    ettes
    2.06
    ľ
    2.01
    ¯
    2.01
    ffer
    1.99
    ¿
    1.89
    µ
    1.89
    Activations Density 0.174%

    No Known Activations