© 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. 29781
    Prev
    Next
    INDEX
    Explanations

    references to methodologies in various 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
    156
    +0.36
    2.3%
    376
    +0.21
    1.4%
    413
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    156
    +0.36
    0.01
    365
    +0.21
    0.01
    413
    +0.12
    0.01
    Negative Logits
    §
    -2.02
    ĥ½
    -1.86
    »¿
    -1.75
    ounder
    -1.62
    Ĵ
    -1.61
    aucoup
    -1.60
    ĵ
    -1.45
     fortune
    -1.43
     booked
    -1.42
    ONS
    -1.42
    POSITIVE LOGITS
    ically
    1.86
    imetry
    1.81
    igraph
    1.64
    amente
    1.62
    igraphy
    1.60
    ics
    1.59
    ical
    1.54
    eral
    1.42
    ica
    1.39
    cue
    1.39
    Activations Density 0.010%

    No Known Activations