© 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 EvalsExportsAPI 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. 28802
    Prev
    Next
    INDEX
    Explanations

    occurrences of the keyword "OUT"

    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
    52
    +0.12
    0.7%
    457
    +0.11
    0.7%
    111
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    52
    +0.12
    0.01
    108
    +0.11
    0.01
    420
    +0.11
    0.01
    Negative Logits
    omitempty
    -1.65
    ismiss
    -1.51
    ellants
    -1.51
    oxacin
    -1.49
    izumab
    -1.45
    ytics
    -1.42
    acial
    -1.41
    )\|_{
    -1.41
    urred
    -1.40
    umatic
    -1.39
    POSITIVE LOGITS
    £
    2.12
    nier
    1.91
    vre
    1.81
    ière
    1.77
    ļ
    1.72
    LINE
    1.68
    dale
    1.68
    hole
    1.67
    ł
    1.63
     positions
    1.60
    Activations Density 0.017%

    No Known Activations