© 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. 29696
    Prev
    Next
    INDEX
    Explanations

    mentions of gender-related terms

    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
    87
    +0.15
    0.9%
    119
    +0.13
    0.8%
    457
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    419
    +0.15
    0.01
    484
    +0.13
    0.01
    457
    +0.12
    0.01
    Negative Logits
     applicable
    -1.80
     proven
    -1.44
    oded
    -1.42
    uing
    -1.40
     terminating
    -1.36
    inguished
    -1.36
     OF
    -1.33
     written
    -1.32
    ues
    -1.31
    ider
    -1.30
    POSITIVE LOGITS
    "}](#
    2.21
    scripts
    1.77
    zilla
    1.64
    jam
    1.64
     Rapids
    1.62
    craft
    1.59
    vars
    1.59
    iors
    1.55
    wiki
    1.52
    webpack
    1.50
    Activations Density 0.021%

    No Known Activations