© 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. 26615
    Prev
    Next
    INDEX
    Explanations

    repeated instances of the token "aca"

    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%
    43
    +0.12
    0.7%
    180
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    31
    +0.14
    0.01
    43
    +0.12
    0.01
    499
    +0.11
    0.01
    Negative Logits
    ¿½
    -2.18
    ĵ
    -2.14
    ı
    -2.08
    ĥ½
    -2.03
    ĭ
    -1.99
    Ĥ
    -1.95
    ))$.
    -1.77
    ij
    -1.75
    ))$
    -1.69
    ))$,
    -1.68
    POSITIVE LOGITS
    pora
    1.92
    vre
    1.71
    ovsky
    1.68
    cule
    1.68
    issance
    1.68
     cooker
    1.66
    kowski
    1.66
    FW
    1.65
    fors
    1.64
    ophone
    1.63
    Activations Density 0.011%

    No Known Activations