© 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. 26186
    Prev
    Next
    INDEX
    Explanations

    instances of the word "requested"

    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
    +0.26
    1.6%
    156
    +0.23
    1.3%
    387
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    387
    +0.26
    0.02
    277
    +0.23
    0.02
    310
    +0.16
    0.02
    Negative Logits
    enson
    -2.04
    phrine
    -1.86
    Verlag
    -1.76
    ksen
    -1.67
    POINT
    -1.62
    ifies
    -1.56
    minded
    -1.54
    ski
    -1.54
    son
    -1.52
    ened
    -1.47
    POSITIVE LOGITS
    ¤
    2.57
    ¨
    2.52
    Ļ
    2.49
    ij
    2.37
    °
    2.36
    Ĺ
    2.36
    ģ
    2.34
    ĻĤ
    2.26
    ľ
    2.25
    Ī
    2.21
    Activations Density 0.012%

    No Known Activations