Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 28981
    Prev
    Next
    INDEX
    Explanations

    mentions of professors and academic credentials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/2-res-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_resid_post
    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
    258
    +0.12
    0.7%
    10
    +0.12
    0.6%
    132
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    418
    +0.12
    -0.00
    34
    +0.12
    0.05
    365
    +0.12
    0.03
    Negative Logits
    Ł
    -1.86
    ĥ½
    -1.84
    Ľ
    -1.78
    ¯
    -1.69
     exceptions
    -1.62
    ĨĴ
    -1.60
    ĵ
    -1.60
    į
    -1.57
     audible
    -1.56
    bered
    -1.55
    POSITIVE LOGITS
     professor
    2.04
     university
    2.00
    fessor
    1.95
     thesis
    1.94
    student
    1.91
     studying
    1.89
     honors
    1.89
     graduate
    1.78
     Professor
    1.76
     Graduate
    1.74
    Activations Density 0.386%

    No Known Activations