© 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. 25934
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "set up."

    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
    455
    +0.13
    0.7%
    263
    +0.11
    0.6%
    223
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    455
    +0.13
    0.03
    465
    +0.11
    0.03
    263
    +0.11
    0.03
    Negative Logits
    ĻĤ
    -1.76
    ħ
    -1.59
     properties
    -1.52
    sat
    -1.48
    iated
    -1.47
     periods
    -1.47
    ated
    -1.47
    iating
    -1.44
     threads
    -1.39
     phosphatase
    -1.36
    POSITIVE LOGITS
    acity
    1.43
    lando
    1.42
    icians
    1.42
    lington
    1.42
    .).
    1.41
    rente
    1.38
    reet
    1.37
    ramento
    1.36
    rsquo
    1.34
     meant
    1.30
    Activations Density 0.182%

    No Known Activations