© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 27945
    Prev
    Next
    INDEX
    Explanations

    the phrase "at all" in various 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
    495
    +0.14
    0.7%
    477
    +0.13
    0.7%
    132
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.14
    0.12
    426
    +0.13
    0.11
    480
    +0.12
    0.10
    Negative Logits
    ↵↵
    -3.28
    č↵
    -3.28
    ↵
    -3.28
    -3.28
     ↵
    -3.28
    ↵
    -3.28
     ↵
    -3.28
    <|outofrange|>
    -3.28
    -3.28
    <|outofrange|>
    -3.28
    POSITIVE LOGITS
    lag
    1.66
    eon
    1.62
    osph
    1.48
    amy
    1.48
    watson
    1.45
    hops
    1.43
    arts
    1.43
    esty
    1.43
    adier
    1.42
    respect
    1.41
    Activations Density 0.257%

    No Known Activations