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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 28416
    Prev
    Next
    INDEX
    Explanations

    occurrences of the letter 't' 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__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    34
    +0.11
    0.7%
    369
    +0.11
    0.6%
    372
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    34
    +0.11
    0.10
    128
    +0.11
    0.08
    354
    +0.10
    0.07
    Negative Logits
     said
    -1.75
    áĢº
    -1.72
    ி
    -1.70
    àµį
    -1.69
    áĢ¯
    -1.68
    à¯
    -1.67
    àµ
    -1.66
    à°¿
    -1.62
    e
    -1.58
    à¯ģ
    -1.56
    POSITIVE LOGITS
    anks
    1.84
    issue
    1.70
    aurus
    1.68
    DNA
    1.64
    elesc
    1.63
    iana
    1.56
    reads
    1.48
    CoV
    1.48
     rocket
    1.48
    liche
    1.47
    Activations Density 1.324%

    No Known Activations