© 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. 30774
    Prev
    Next
    INDEX
    Explanations

    occurrences of special characters or symbols

    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
    2
    +0.15
    0.9%
    410
    +0.14
    0.8%
    111
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.15
    0.01
    410
    +0.14
    0.01
    2
    +0.13
    0.01
    Negative Logits
    OLOR
    -1.63
    '?
    -1.55
    ialog
    -1.53
    "?
    -1.50
    amples
    -1.48
    )?
    -1.45
    romycin
    -1.44
    à°¿
    -1.39
    opes
    -1.36
    ylase
    -1.35
    POSITIVE LOGITS
    laws
    1.85
    fileID
    1.49
    xiv
    1.46
    cit
    1.45
    fire
    1.43
    cies
    1.41
    require
    1.39
    selves
    1.37
    lee
    1.37
    shots
    1.36
    Activations Density 0.014%

    No Known Activations