© 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. 25833
    Prev
    Next
    INDEX
    Explanations

    phrases indicating certainty or legal decisions

    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
    167
    +0.11
    0.6%
    41
    +0.11
    0.6%
    114
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.11
    0.16
    106
    +0.11
    0.14
    136
    +0.11
    0.14
    Negative Logits
    áĢº
    -1.68
    atri
    -1.60
    documentclass
    -1.59
    ĨĴ
    -1.53
    ping
    -1.51
    oti
    -1.48
    fare
    -1.43
    à¯į
    -1.37
    ercise
    -1.37
    helial
    -1.34
    POSITIVE LOGITS
     precision
    1.67
    ably
    1.65
     partnership
    1.50
     nonetheless
    1.48
    inct
    1.47
    unity
    1.43
     cartridges
    1.42
    endment
    1.36
     engines
    1.35
     collaboration
    1.35
    Activations Density 1.657%

    No Known Activations