© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27206
    Prev
    Next
    INDEX
    Explanations

    mentions of "campus."

    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
    +0.19
    1.1%
    467
    +0.14
    0.8%
    91
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    91
    +0.19
    0.02
    467
    +0.14
    0.02
    145
    +0.13
    0.02
    Negative Logits
    ĥ½
    -2.15
    ĥ
    -2.02
    hin
    -1.70
    ĨĴ
    -1.69
    alus
    -1.64
    ¯
    -1.60
    §
    -1.58
    ı
    -1.51
    ³
    -1.48
    shore
    -1.44
    POSITIVE LOGITS
    yard
    2.05
    istry
    1.92
    yards
    1.90
    notes
    1.84
    manship
    1.75
    "?
    1.73
     affairs
    1.66
    note
    1.65
    positions
    1.64
    plates
    1.62
    Activations Density 0.012%

    No Known Activations