© 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. 26104
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and financial documents

    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
    482
    +0.12
    0.6%
    283
    +0.10
    0.6%
    52
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    279
    +0.12
    0.08
    112
    +0.10
    0.10
    484
    +0.10
    -0.01
    Negative Logits
    ittal
    -1.86
    sson
    -1.76
    itative
    -1.73
    ."[
    -1.67
    ille
    -1.63
    ctomy
    -1.58
    ikel
    -1.55
     thereon
    -1.53
    ]'
    -1.50
    velope
    -1.48
    POSITIVE LOGITS
    panic
    1.66
    disambiguation
    1.50
    places
    1.47
     because
    1.45
     caf
    1.39
    crystall
    1.37
    Ł
    1.37
     racism
    1.34
     ops
    1.33
    ?:
    1.29
    Activations Density 3.201%

    No Known Activations