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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26494
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "amino" and related terms in a biological context

    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
    201
    +0.12
    0.7%
    511
    +0.11
    0.6%
    371
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    511
    +0.12
    0.01
    213
    +0.11
    0.03
    491
    +0.11
    0.02
    Negative Logits
    wives
    -1.69
    disambiguation
    -1.62
    )'
    -1.56
    minster
    -1.54
    taire
    -1.52
    rosophila
    -1.51
    bn
    -1.50
    %),
    -1.47
    $),
    -1.47
    '),
    -1.47
    POSITIVE LOGITS
    ulous
    1.60
    ^**
    1.50
     stat
    1.48
     debt
    1.46
     **(
    1.45
     artifacts
    1.45
     disc
    1.44
     forth
    1.43
    rift
    1.41
    orphic
    1.40
    Activations Density 0.233%

    No Known Activations