© 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. 27231
    Prev
    Next
    INDEX
    Explanations

    occurrences of assists and rebounds in statistical contexts

    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
    471
    +0.12
    0.7%
    273
    +0.11
    0.6%
    260
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    273
    +0.12
    0.01
    471
    +0.11
    0.01
    109
    +0.11
    0.01
    Negative Logits
    ubert
    -1.76
    hthal
    -1.75
    uses
    -1.69
    utes
    -1.61
    uw
    -1.57
    rous
    -1.54
    usement
    -1.54
    ael
    -1.52
    tv
    -1.48
    appropri
    -1.46
    POSITIVE LOGITS
    ¶
    2.25
    º
    2.21
    µ
    2.15
    ł
    2.12
    ĸ
    2.03
    ģ
    2.03
    «
    1.98
    ¹
    1.97
    ¼
    1.96
    ¤
    1.94
    Activations Density 0.010%

    No Known Activations