© 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. 29472
    Prev
    Next
    INDEX
    Explanations

    instances of "inner" and "outer" in relation to contexts such as spirituality or technical specifications

    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
    362
    +0.16
    1.0%
    376
    +0.14
    0.9%
    99
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    420
    +0.16
    0.01
    99
    +0.14
    0.01
    362
    +0.12
    0.01
    Negative Logits
    ĵ
    -3.70
    ĥ½
    -3.69
    ĨĴ
    -3.57
    ľ
    -3.55
    Ī
    -3.32
    ĺ
    -3.08
    »¿
    -3.08
    Ĥ
    -3.07
    Īĺ
    -3.05
    ³
    -2.95
    POSITIVE LOGITS
    fried
    1.81
    furt
    1.80
    amente
    1.78
    iza
    1.77
    fors
    1.75
    nement
    1.70
    ailed
    1.69
     era
    1.67
    agem
    1.65
     area
    1.63
    Activations Density 0.013%

    No Known Activations