© 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. 26313
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "Bl" indicating a reference to a specific topic or term related to the context

    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
    477
    +0.16
    0.9%
    59
    +0.15
    0.8%
    369
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.16
    0.02
    477
    +0.15
    0.02
    354
    +0.11
    0.02
    Negative Logits
     decl
    -1.58
    Ĭ
    -1.55
    rian
    -1.55
    )>
    -1.53
    '?"
    -1.48
    )$)
    -1.48
     suppose
    -1.48
     slightest
    -1.47
     ?"
    -1.46
    ria
    -1.45
    POSITIVE LOGITS
    uetooth
    1.97
    adder
    1.82
    rock
    1.74
    ouin
    1.68
    isters
    1.67
    ings
    1.62
    walk
    1.61
    endar
    1.57
    launchpad
    1.56
    auer
    1.55
    Activations Density 0.038%

    No Known Activations