© 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. 30194
    Prev
    Next
    INDEX
    Explanations

    names and surnames, particularly with strong emphasis on "owski."

    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
    156
    +0.24
    1.4%
    363
    +0.12
    0.7%
    466
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    363
    +0.24
    0.03
    43
    +0.12
    0.03
    370
    +0.11
    0.03
    Negative Logits
    ĥ½
    -2.01
     FIG
    -1.65
    ?’
    -1.57
    inations
    -1.55
    .?
    -1.54
    ureus
    -1.50
    ĺ
    -1.47
    ences
    -1.47
    $/
    -1.44
     anything
    -1.43
    POSITIVE LOGITS
    ÅĦ
    1.93
    vist
    1.59
    jee
    1.54
    ew
    1.48
    vill
    1.46
    atche
    1.45
    pora
    1.44
    Supporting
    1.43
    esque
    1.41
    velt
    1.39
    Activations Density 0.079%

    No Known Activations