© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 27886
    Prev
    Next
    INDEX
    Explanations

    patterns and structures in text

    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
    23
    +0.27
    1.6%
    478
    +0.18
    1.1%
    206
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    383
    +0.27
    0.14
    206
    +0.18
    0.14
    50
    +0.12
    0.13
    Negative Logits
    :
    -2.04
    creen
    -1.78
    ieux
    -1.74
    %;
    -1.69
    opan
    -1.69
    ista
    -1.69
    :-
    -1.68
    heets
    -1.67
    :`
    -1.62
    ?:
    -1.55
    POSITIVE LOGITS
     latter
    1.68
    ĥ½
    1.63
    ¯
    1.61
     ‘
    1.52
    Ĥ
    1.47
    existence
    1.47
    leans
    1.47
    ä½ķ
    1.44
    ²
    1.43
    į
    1.42
    Activations Density 0.530%

    No Known Activations