© 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. 27185
    Prev
    Next
    INDEX
    Explanations

    instances of the word "create."

    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
    +0.17
    1.0%
    376
    +0.17
    1.0%
    30
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    30
    +0.17
    0.02
    389
    +0.17
    0.02
    3
    +0.16
    0.01
    Negative Logits
    unnumbered
    -1.98
    inen
    -1.80
    "`
    -1.71
    Ñıв
    -1.71
    }"
    -1.57
    ÑĨиÑı
    -1.51
    want
    -1.50
    omitempty
    -1.49
    ÑĨии
    -1.48
    uen
    -1.47
    POSITIVE LOGITS
    castle
    1.95
    able
    1.77
    idable
    1.68
    zilla
    1.63
    freak
    1.60
    eto
    1.57
    icip
    1.56
     safety
    1.49
     life
    1.47
    ulence
    1.42
    Activations Density 0.013%

    No Known Activations