© 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. 25936
    Prev
    Next
    INDEX
    Explanations

    sentences and segments in the text that provide factual information or conclusions

    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
    315
    +0.15
    0.8%
    355
    +0.15
    0.8%
    292
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.15
    0.55
    56
    +0.15
    0.18
    203
    +0.13
    0.38
    Negative Logits
    Īĺ
    -2.64
    ¡
    -2.35
    İ
    -2.04
    Ľ
    -1.97
    ł
    -1.92
    ·
    -1.90
    IJ
    -1.88
    ĥ
    -1.86
    ·¸
    -1.82
    ³
    -1.81
    POSITIVE LOGITS
    ova
    1.67
    eva
    1.62
    )](
    1.61
    atche
    1.61
    ev
    1.57
    resa
    1.52
    inos
    1.50
    omin
    1.47
    flower
    1.45
    tur
    1.41
    Activations Density 3.556%

    No Known Activations