© 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. 28740
    Prev
    Next
    INDEX
    Explanations

    expressions of support or endorsement

    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
    376
    +0.27
    1.5%
    140
    +0.11
    0.6%
    38
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.27
    0.01
    140
    +0.11
    0.01
    472
    +0.10
    0.01
    Negative Logits
    keit
    -1.68
    rue
    -1.63
    sel
    -1.62
    shire
    -1.57
    roy
    -1.55
     ashamed
    -1.49
    RA
    -1.49
    wikipedia
    -1.48
    s
    -1.48
    inkle
    -1.47
    POSITIVE LOGITS
     crop
    1.62
    ļ
    1.53
    oter
    1.51
    olin
    1.49
    omen
    1.45
    flies
    1.44
    Ļ
    1.44
     teeth
    1.43
    icolor
    1.40
     ammunition
    1.38
    Activations Density 0.012%

    No Known Activations