© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 2-MLP-SM
    6. 26095
    Prev
    Next
    INDEX
    Explanations

    references to antigens and immunological markers

    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
    58
    +0.14
    0.8%
    478
    +0.13
    0.7%
    23
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    58
    +0.14
    0.03
    23
    +0.13
    0.01
    478
    +0.12
    0.03
    Negative Logits
    Ĺ
    -3.38
    ¶
    -3.23
    º
    -3.17
    £
    -3.15
    ¢
    -3.14
    ·¸
    -3.09
    ł
    -3.06
    ¡
    -3.06
    Ļ
    -3.04
    ķ
    -2.99
    POSITIVE LOGITS
     enough
    1.64
     theirs
    1.61
     EIGEN
    1.58
    ffield
    1.52
     BSD
    1.52
     yours
    1.50
     harder
    1.47
     someone
    1.47
     worth
    1.46
     GitHub
    1.46
    Activations Density 0.134%

    No Known Activations