© 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. 26265
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals, particularly Rick Perry and other names associated with significant events or contexts

    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
    369
    +0.24
    1.4%
    156
    +0.21
    1.2%
    100
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    71
    +0.24
    0.03
    369
    +0.21
    0.03
    370
    +0.13
    0.03
    Negative Logits
    Ĵ
    -2.11
    ĥ½
    -2.06
    ĺ
    -1.99
    ķ
    -1.92
    irmat
    -1.73
    ility
    -1.71
    ¥
    -1.70
     ages
    -1.66
    °
    -1.65
    ĵ
    -1.65
    POSITIVE LOGITS
    shire
    1.81
    genstein
    1.76
    schild
    1.75
    spe
    1.65
    able
    1.51
    :"
    1.48
    sburg
    1.45
    tees
    1.44
    craft
    1.43
    mons
    1.43
    Activations Density 0.058%

    No Known Activations