© 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. 26511
    Prev
    Next
    INDEX
    Explanations

    negative evaluations or judgments

    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
    156
    +0.15
    0.9%
    99
    +0.14
    0.8%
    407
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.15
    0.04
    360
    +0.14
    0.04
    407
    +0.13
    0.04
    Negative Logits
    ERY
    -1.44
     undefined
    -1.42
    ivist
    -1.37
    acial
    -1.37
    YLE
    -1.35
    ONS
    -1.34
    ESH
    -1.33
    iona
    -1.33
    acebook
    -1.33
    ó
    -1.32
    POSITIVE LOGITS
    ĻĤ
    2.12
    gered
    1.95
     enough
    1.90
    ieux
    1.83
     habits
    1.83
    rums
    1.78
    guy
    1.72
    fellow
    1.71
     ones
    1.70
    Ĥ¬
    1.68
    Activations Density 0.040%

    No Known Activations