© 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. 26457
    Prev
    Next
    INDEX
    Explanations

    references to the speaker or personal pronouns indicating self-identity

    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
    36
    +0.16
    0.9%
    373
    +0.14
    0.8%
    412
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.16
    0.02
    391
    +0.14
    0.02
    309
    +0.13
    0.02
    Negative Logits
     paints
    -1.54
    ainen
    -1.46
     accordingly
    -1.46
     Rim
    -1.45
     Leone
    -1.40
    arious
    -1.39
    itzer
    -1.38
     Mort
    -1.36
     off
    -1.35
     Film
    -1.34
    POSITIVE LOGITS
    theorem
    1.84
    >(
    1.63
    Theorem
    1.59
    mining
    1.57
    áĢ¬
    1.55
    EX
    1.55
    dAtA
    1.51
    equation
    1.49
    >()
    1.49
    CONST
    1.43
    Activations Density 0.002%

    No Known Activations