© 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. 29307
    Prev
    Next
    INDEX
    Explanations

    references to digital data representation and processing, particularly in the context of bit manipulations

    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
    99
    +0.12
    0.6%
    2
    +0.11
    0.6%
    214
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.12
    0.02
    406
    +0.11
    0.02
    99
    +0.11
    0.02
    Negative Logits
    ·¸
    -2.18
    Ĩ
    -1.91
    Ĥ¬
    -1.86
    Ĥ
    -1.68
    ¹
    -1.66
    ¼
    -1.56
    ª
    -1.54
    ĨĴ
    -1.54
     myself
    -1.46
     cref
    -1.45
    POSITIVE LOGITS
    coin
    1.93
    itud
    1.82
    stadt
    1.81
    zone
    1.78
     Instruments
    1.71
    thal
    1.70
    bank
    1.68
    recht
    1.67
    haw
    1.67
    enstein
    1.63
    Activations Density 0.018%

    No Known Activations