© 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. 26113
    Prev
    Next
    INDEX
    Explanations

    references to numerical quantities and semantic descriptors within 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/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
    156
    +0.28
    1.6%
    271
    +0.17
    1.0%
    223
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.28
    0.83
    156
    +0.17
    0.83
    71
    +0.14
    0.82
    Negative Logits
    $]{};
    -1.60
    zez
    -1.51
    leep
    -1.51
     upside
    -1.49
    qrt
    -1.45
     logarithm
    -1.43
    orect
    -1.42
    oho
    -1.41
    ypse
    -1.38
    ...](
    -1.35
    POSITIVE LOGITS
     reactions
    1.46
     fever
    1.46
    ,^[@
    1.45
     interpretations
    1.44
    .^[@
    1.36
    [^
    1.35
    ural
    1.32
     papers
    1.31
     stresses
    1.30
    ´
    1.30
    Activations Density 4.304%

    No Known Activations