© 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. 25825
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "role."

    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
    +0.17
    1.0%
    260
    +0.13
    0.7%
    184
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.17
    0.04
    133
    +0.13
    0.04
    260
    +0.12
    0.03
    Negative Logits
     Holocaust
    -1.58
     kindness
    -1.47
     Fiction
    -1.46
    sole
    -1.45
    scribe
    -1.45
     mind
    -1.42
     Trust
    -1.40
     least
    -1.39
     me
    -1.38
     anything
    -1.37
    POSITIVE LOGITS
    aditional
    1.80
    hole
    1.78
    holes
    1.64
    arily
    1.55
    func
    1.52
    ball
    1.51
    umbo
    1.50
    adition
    1.47
    emption
    1.45
    abor
    1.44
    Activations Density 2.916%

    No Known Activations