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. 26916
    Prev
    Next
    INDEX
    Explanations

    phrases or clauses containing the preposition "of"

    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
    23
    +0.16
    0.9%
    69
    +0.14
    0.8%
    457
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.16
    0.10
    457
    +0.14
    0.08
    98
    +0.14
    -0.00
    Negative Logits
    ī
    -2.12
     behind
    -1.66
    ı
    -1.64
    İ
    -1.64
    Ĩ
    -1.57
    ħ
    -1.49
    »¿
    -1.47
    "—
    -1.47
    ĭ
    -1.46
    Ł
    -1.45
    POSITIVE LOGITS
    pcbi
    2.26
    ppat
    1.77
    pgen
    1.74
    pez
    1.60
    ↵Č
    1.57
     Proposition
    1.52
    pone
    1.49
     Lemma
    1.47
    itzer
    1.47
    ousal
    1.46
    Activations Density 0.680%

    No Known Activations