© 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. 28618
    Prev
    Next
    INDEX
    Explanations

    references to fixtures in programming or design contexts

    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
    413
    +0.13
    0.7%
    392
    +0.13
    0.7%
    156
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    392
    +0.13
    0.01
    413
    +0.13
    0.01
    178
    +0.11
    0.01
    Negative Logits
    §
    -3.93
    ¦
    -3.69
    Ħ
    -3.63
    Ĵ
    -3.60
    ĻĤ
    -3.58
    ´
    -3.52
    Īĺ
    -3.48
    ľĵ
    -3.48
    Ĩ
    -3.40
    Ĺ
    -3.39
    POSITIVE LOGITS
    cript
    1.93
    peak
    1.93
    dorff
    1.80
    atory
    1.76
    erville
    1.70
    wagen
    1.69
    eful
    1.69
    erve
    1.67
    oft
    1.66
    "}](#
    1.64
    Activations Density 0.025%

    No Known Activations