© 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. 26431
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Class" in various contexts, particularly related to programming or code structures

    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
    247
    +0.13
    0.7%
    431
    +0.12
    0.7%
    457
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    431
    +0.13
    0.03
    247
    +0.12
    0.02
    146
    +0.11
    0.02
    Negative Logits
    ·¸
    -2.41
    ´
    -2.32
    ĥ½
    -2.31
    ı
    -2.27
    ³
    -2.26
    İ
    -2.20
    ĸ´
    -2.15
    «
    -2.10
    ¬
    -2.07
    ĩ
    -2.03
    POSITIVE LOGITS
    ification
    1.93
    ifications
    1.88
    ified
    1.85
    ify
    1.81
    ics
    1.76
    ical
    1.73
    ifically
    1.70
    ific
    1.70
    ÃŃs
    1.68
    istically
    1.68
    Activations Density 0.316%

    No Known Activations