© 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. 2-MLP-SM
    11. 22917
    Prev
    Next
    INDEX
    Explanations

    references to historical or significant artifacts and their 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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    70
    +0.12
    0.7%
    145
    +0.12
    0.7%
    266
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.12
    0.08
    497
    +0.12
    0.02
    266
    +0.11
    0.02
    Negative Logits
    -1.58
    >;
    -1.56
    -1.49
     merged
    -1.41
     spanned
    -1.39
    ?:
    -1.39
    olite
    -1.39
    ){
    -1.34
     architect
    -1.32
    [_
    -1.30
    POSITIVE LOGITS
    ↵  âĢĥ
    2.44
    2.44
    2.44
    ↵    ↵
    2.44
    <|outofrange|>
    2.44
    2.44
    <|outofrange|>
    2.44
    2.44
    <|outofrange|>
    2.44
    2.44
    Activations Density 0.991%

    No Known Activations