© 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. 27730
    Prev
    Next
    INDEX
    Explanations

    instances of the word "coh" in various forms

    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
    148
    +0.14
    0.8%
    43
    +0.13
    0.7%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.02
    410
    +0.13
    0.01
    43
    +0.12
    0.01
    Negative Logits
    ĨĴ
    -2.82
    ·¸
    -2.04
    į
    -1.98
    IJ
    -1.93
    Ĥ¬
    -1.91
    <|outofrange|>
    -1.83
    ↵
    -1.83
    -1.83
    -1.83
    č↵
    -1.83
    POSITIVE LOGITS
     snaps
    1.69
    stown
    1.63
    pool
    1.63
    ousing
    1.54
    --
    1.53
     trips
    1.49
    round
    1.40
    orate
    1.40
    eston
    1.39
    omology
    1.39
    Activations Density 0.021%

    No Known Activations