© 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. 29268
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific function calls in the code

    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
    414
    +0.13
    0.7%
    139
    +0.12
    0.7%
    235
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.13
    0.22
    185
    +0.12
    0.17
    165
    +0.11
    0.17
    Negative Logits
    hem
    -1.63
    hens
    -1.63
    pson
    -1.59
    boro
    -1.58
    omorphisms
    -1.54
    pez
    -1.48
    ´
    -1.47
     publication
    -1.47
    inherit
    -1.47
    ford
    -1.47
    POSITIVE LOGITS
    rpm
    1.54
     rpm
    1.43
    dered
    1.42
     Opposition
    1.42
    night
    1.40
    iative
    1.39
     contradicts
    1.36
    illion
    1.36
     reminds
    1.35
    true
    1.34
    Activations Density 0.389%

    No Known Activations