© 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. 28397
    Prev
    Next
    INDEX
    Explanations

    references to inner aspects or components

    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%
    111
    +0.13
    0.7%
    266
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.16
    0.02
    266
    +0.13
    0.02
    99
    +0.13
    0.02
    Negative Logits
    ĵ
    -2.44
    ľ
    -2.31
    ĥ
    -2.26
    ĨĴ
    -2.20
    Ŀ
    -2.13
    Ķ
    -2.10
    ĩ
    -2.09
    Ľ
    -2.03
    ¯
    -1.98
    ĸ
    -1.97
    POSITIVE LOGITS
    het
    1.75
    fried
    1.64
    gest
    1.60
     affairs
    1.54
    notes
    1.47
    range
    1.47
    umerable
    1.47
     ones
    1.46
    hart
    1.43
    usalem
    1.39
    Activations Density 0.294%

    No Known Activations