© 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. 25478
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific template markers or syntax in programming or markup languages

    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
    427
    +0.12
    0.7%
    98
    +0.11
    0.6%
    222
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.12
    0.55
    56
    +0.11
    0.18
    203
    +0.11
    0.38
    Negative Logits
    ¯
    -4.51
    ª
    -4.43
    «
    -4.37
    ĻĤ
    -4.32
    ī
    -4.29
    Ĺ
    -4.26
    Ļ
    -4.18
    ²
    -4.17
    Į
    -4.13
    ¿½
    -4.06
    POSITIVE LOGITS
    es
    1.71
    tery
    1.65
    est
    1.63
    s
    1.49
    chten
    1.48
    er
    1.44
     à°
    1.44
     casc
    1.43
     descent
    1.42
    around
    1.42
    Activations Density 3.564%

    No Known Activations