© 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. 29271
    Prev
    Next
    INDEX
    Explanations

    instances of the word "withdrawal."

    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
    +0.16
    1.0%
    217
    +0.13
    0.7%
    115
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.16
    0.01
    122
    +0.13
    0.01
    474
    +0.12
    0.01
    Negative Logits
    '>
    -1.73
    ^](#
    -1.69
    ©
    -1.68
    ¿
    -1.59
    »¿
    -1.58
    Ĥ¬
    -1.53
    arl
    -1.53
    Jewish
    -1.50
    ĥ½
    -1.49
    gger
    -1.46
    POSITIVE LOGITS
     chambers
    1.80
    ions
    1.73
     pains
    1.69
    idable
    1.66
     occurs
    1.64
    ives
    1.58
     triggers
    1.58
     scenes
    1.54
     valves
    1.54
     compartments
    1.54
    Activations Density 0.008%

    No Known Activations