© 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. 28544
    Prev
    Next
    INDEX
    Explanations

    instances of the word "close" and its variations, indicating proximity or intimacy

    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
    0.9%
    172
    +0.13
    0.8%
    444
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    181
    +0.16
    0.04
    342
    +0.13
    0.04
    172
    +0.13
    0.04
    Negative Logits
    atile
    -1.67
    ĨĴ
    -1.59
    Ķ
    -1.55
    ylum
    -1.55
    Ł
    -1.51
    ĵ
    -1.48
    ©
    -1.47
    Ĭ
    -1.45
    icrosoft
    -1.41
    ¯
    -1.40
    POSITIVE LOGITS
    abouts
    1.94
    frames
    1.94
     enough
    1.71
    frame
    1.71
    liness
    1.68
    ings
    1.67
    fix
    1.65
    liest
    1.59
    ups
    1.56
    dated
    1.52
    Activations Density 0.034%

    No Known Activations