© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27210
    Prev
    Next
    INDEX
    Explanations

    occurrences of the symbol "ÃĹ" which seems to represent a placeholder or specific data point in the text

    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
    334
    +0.14
    0.8%
    377
    +0.12
    0.7%
    97
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    334
    +0.14
    0.01
    377
    +0.12
    0.01
    97
    +0.12
    0.01
    Negative Logits
    utors
    -1.78
    rence
    -1.59
    ausing
    -1.59
    osing
    -1.57
    angling
    -1.55
    unt
    -1.54
    ·¸
    -1.53
    uting
    -1.50
    ¹
    -1.50
    astically
    -1.49
    POSITIVE LOGITS
    plots
    1.72
    chitz
    1.67
    scribed
    1.61
     Comic
    1.53
    hered
    1.51
    oured
    1.49
    ière
    1.46
    skins
    1.44
    minist
    1.39
    Verlag
    1.37
    Activations Density 0.016%

    No Known Activations