© 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 EvalsExportsAPI 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. 28691
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "sky"

    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
    246
    +0.13
    0.7%
    330
    +0.12
    0.7%
    269
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.13
    0.01
    246
    +0.12
    0.01
    489
    +0.11
    0.01
    Negative Logits
     saline
    -1.57
     late
    -1.54
    <!--
    -1.52
     strept
    -1.42
     Respondent
    -1.40
     Later
    -1.39
     written
    -1.37
     middle
    -1.35
     silent
    -1.35
     moderate
    -1.34
    POSITIVE LOGITS
    kot
    1.90
    ÅĽci
    1.77
    works
    1.77
    fors
    1.76
    forge
    1.74
    craft
    1.74
    holm
    1.68
    weather
    1.68
    bank
    1.67
    recht
    1.66
    Activations Density 0.028%

    No Known Activations