© 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. 27174
    Prev
    Next
    INDEX
    Explanations

    the word "flick" and its variations, indicating a focus on quick or sudden actions

    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
    59
    +0.15
    0.9%
    376
    +0.13
    0.8%
    7
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    59
    +0.15
    0.01
    7
    +0.13
    0.01
    230
    +0.11
    0.01
    Negative Logits
    į
    -2.24
    ħ
    -2.09
    ¼
    -2.05
    ½
    -2.04
    ĥ
    -2.02
    Į
    -2.02
    ĭ
    -2.02
    Ĥ¬
    -2.01
    ²
    -1.98
    ³
    -1.94
    POSITIVE LOGITS
    iewicz
    1.74
    opian
    1.74
    ty
    1.69
    sworth
    1.69
    amycin
    1.67
    ifer
    1.65
    ruptcy
    1.62
    walker
    1.58
    bugs
    1.57
    rove
    1.57
    Activations Density 0.019%

    No Known Activations