© 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. 26032
    Prev
    Next
    INDEX
    Explanations

    the word "Will" in various contexts indicating future intent or possibility

    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
    376
    +0.15
    0.8%
    192
    +0.13
    0.7%
    201
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    192
    +0.15
    0.03
    411
    +0.13
    0.02
    201
    +0.12
    0.03
    Negative Logits
    orting
    -1.74
    eah
    -1.66
    ANC
    -1.66
    verting
    -1.54
    OVE
    -1.53
    unnumbered
    -1.51
    atics
    -1.47
    INCLUDING
    -1.45
    cknow
    -1.45
    ITED
    -1.45
    POSITIVE LOGITS
    zier
    1.69
    ful
    1.60
    ough
    1.58
    cox
    1.55
    :=
    1.53
    ¿½
    1.49
    iest
    1.46
    uel
    1.46
    guard
    1.46
    ga
    1.44
    Activations Density 0.214%

    No Known Activations