© 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. 25706
    Prev
    Next
    INDEX
    Explanations

    assertions or statements emphasizing a key point or idea

    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
    +0.14
    0.8%
    412
    +0.12
    0.6%
    174
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    220
    +0.14
    0.04
    174
    +0.12
    0.03
    273
    +0.11
    0.03
    Negative Logits
     Briefly
    -1.70
    ably
    -1.68
    ).](
    -1.41
    )](#
    -1.40
    actin
    -1.38
    )].
    -1.37
    )];
    -1.35
    course
    -1.30
    avour
    -1.29
    )\].
    -1.27
    POSITIVE LOGITS
    áĢº
    1.94
    chers
    1.93
    ched
    1.88
    chy
    1.75
    cher
    1.75
    tics
    1.69
    alia
    1.68
    aliana
    1.62
    ÃŃs
    1.56
    tis
    1.49
    Activations Density 0.694%

    No Known Activations