© 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. 27756
    Prev
    Next
    INDEX
    Explanations

    expressions related to future events or occurrences

    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
    +0.16
    0.9%
    351
    +0.13
    0.8%
    72
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    72
    +0.16
    0.03
    351
    +0.13
    0.03
    21
    +0.13
    0.02
    Negative Logits
    ounding
    -1.69
    ounded
    -1.65
    hire
    -1.57
    rage
    -1.56
     herself
    -1.52
    ERY
    -1.50
    ulk
    -1.45
    ride
    -1.45
     improvement
    -1.44
     College
    -1.41
    POSITIVE LOGITS
    stance
    2.45
    stances
    1.86
    inct
    1.57
    ures
    1.56
     malf
    1.48
     conj
    1.47
    ipes
    1.47
     events
    1.43
    orph
    1.42
    things
    1.41
    Activations Density 0.013%

    No Known Activations