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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 26647
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter "m"

    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
    369
    +0.26
    1.5%
    196
    +0.15
    0.9%
    81
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    196
    +0.26
    0.04
    369
    +0.15
    0.03
    502
    +0.13
    0.03
    Negative Logits
    operative
    -1.57
    atism
    -1.51
    OLOR
    -1.49
    flare
    -1.48
    collapse
    -1.47
    degree
    -1.47
     authors
    -1.46
    quot
    -1.46
    ĥ
    -1.44
    oulos
    -1.44
    POSITIVE LOGITS
    arshal
    1.79
     closely
    1.68
    manship
    1.60
     representing
    1.59
    cn
    1.50
    tb
    1.49
     consisting
    1.47
    ohn
    1.47
     (>
    1.46
    osph
    1.44
    Activations Density 0.082%

    No Known Activations