© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 29931
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the word "in" and its variations

    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
    478
    +0.20
    1.1%
    69
    +0.15
    0.8%
    440
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.20
    0.13
    440
    +0.15
    0.11
    282
    +0.11
    0.09
    Negative Logits
    ulations
    -1.76
    ingly
    -1.70
    liche
    -1.66
    sworth
    -1.65
    umbing
    -1.61
    itious
    -1.59
    wise
    -1.59
     inactivated
    -1.54
     certificates
    -1.53
    ings
    -1.53
    POSITIVE LOGITS
    eligible
    2.01
     tandem
    1.98
     addition
    1.97
     order
    1.95
    verte
    1.91
    »¿
    1.90
    appropri
    1.90
    ĻĤ
    1.87
     lieu
    1.82
     conjunction
    1.81
    Activations Density 0.669%

    No Known Activations