© 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. 29805
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "sv"

    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
    376
    +0.15
    0.9%
    256
    +0.15
    0.9%
    206
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    256
    +0.15
    0.01
    206
    +0.15
    0.01
    300
    +0.13
    0.01
    Negative Logits
     chance
    -1.74
     hope
    -1.72
    hover
    -1.65
    seeing
    -1.53
    leftarrow
    -1.52
     suppose
    -1.52
    osevelt
    -1.50
    "?"
    -1.50
    aneously
    -1.48
    leftrightarrow
    -1.45
    POSITIVE LOGITS
    ariate
    1.95
    elist
    1.62
     precedent
    1.61
    endor
    1.60
    etable
    1.56
    ista
    1.55
    haus
    1.55
     industry
    1.50
    enson
    1.48
     (“
    1.48
    Activations Density 0.008%

    No Known Activations