© 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. 28602
    Prev
    Next
    INDEX
    Explanations

    various forms of attention, commitment, or action plans related to progress in a task or objective

    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
    175
    +0.14
    0.8%
    348
    +0.11
    0.6%
    196
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.14
    0.40
    53
    +0.11
    0.42
    56
    +0.11
    0.11
    Negative Logits
     telephone
    -1.61
    dates
    -1.49
    icos
    -1.47
     Pictures
    -1.45
     rail
    -1.42
    >/
    -1.41
    ita
    -1.40
    ffect
    -1.32
    ificantly
    -1.31
    ().
    -1.31
    POSITIVE LOGITS
    ĻĤ
    3.86
    £
    3.77
    ¡
    3.66
    ĥ½
    3.63
    ¹
    3.53
    ķ
    3.52
    Īĺ
    3.50
    ·
    3.46
    ĸ´
    3.45
    Ĥ
    3.45
    Activations Density 4.657%

    No Known Activations