© 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 EvalsExportsAPI 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. 28941
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups that are considered vulnerable or disadvantaged

    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
    +0.22
    1.3%
    347
    +0.12
    0.7%
    376
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    347
    +0.22
    0.01
    360
    +0.12
    0.01
    42
    +0.11
    0.01
    Negative Logits
    je
    -1.56
     Appeal
    -1.32
    Scott
    -1.32
    ĥ½
    -1.29
    Af
    -1.28
    OG
    -1.28
    iless
    -1.27
    >&
    -1.26
     perfect
    -1.23
    ____
    -1.23
    POSITIVE LOGITS
     (\<
    1.77
    holder
    1.70
     (\>
    1.68
     portions
    1.65
     passages
    1.64
     positions
    1.63
     populations
    1.63
     roles
    1.60
     situation
    1.59
     compartments
    1.58
    Activations Density 0.015%

    No Known Activations