© 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. 26072
    Prev
    Next
    INDEX
    Explanations

    conditional verbs expressing potentiality or possibility

    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
    202
    +0.16
    0.9%
    376
    +0.15
    0.8%
    486
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    202
    +0.16
    0.10
    486
    +0.15
    0.08
    415
    +0.14
    0.08
    Negative Logits
    Ľ
    -3.42
    »¿
    -3.38
    ¢
    -3.32
    Ŀ
    -3.23
    ¡
    -3.20
    §
    -3.06
    ½
    -2.94
    ł
    -2.85
    »
    -2.78
    £
    -2.70
    POSITIVE LOGITS
     DAMAGE
    1.66
    vas
    1.58
     APPE
    1.49
     KO
    1.49
     abuse
    1.48
    .";
    1.46
     Zar
    1.43
     POSS
    1.42
     NOTICE
    1.42
    ^**
    1.41
    Activations Density 0.649%

    No Known Activations