© 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. 29354
    Prev
    Next
    INDEX
    Explanations

    references to corporations

    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
    +0.17
    0.9%
    59
    +0.12
    0.7%
    90
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    90
    +0.17
    0.02
    240
    +0.12
    0.01
    273
    +0.11
    0.01
    Negative Logits
     pleasure
    -1.57
    ftime
    -1.37
    ableness
    -1.35
     Because
    -1.35
     prow
    -1.33
    icity
    -1.33
     ELSE
    -1.32
    sed
    -1.28
    withstanding
    -1.27
    "?"
    -1.26
    POSITIVE LOGITS
    ipel
    1.75
    urious
    1.59
    ¿½
    1.56
    ulent
    1.56
    ijn
    1.55
    ²
    1.53
    ository
    1.52
    ilage
    1.45
    ulence
    1.45
    us
    1.45
    Activations Density 0.020%

    No Known Activations