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. 28716
    Prev
    Next
    INDEX
    Explanations

    mentions of gendered terms related to boys and girls

    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
    56
    +0.14
    0.8%
    87
    +0.13
    0.8%
    156
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    56
    +0.14
    0.00
    177
    +0.13
    0.02
    76
    +0.13
    0.02
    Negative Logits
    ĥ½
    -1.66
    ¯
    -1.61
    ©
    -1.59
    omycin
    -1.50
    į
    -1.45
    onsense
    -1.44
     effective
    -1.44
    uximab
    -1.43
     others
    -1.41
    illance
    -1.35
    POSITIVE LOGITS
    friends
    2.67
    friend
    2.44
    hood
    2.08
    cott
    1.95
    ward
    1.95
    obi
    1.92
    assertEqual
    1.73
    hoe
    1.66
    fight
    1.65
    boy
    1.63
    Activations Density 0.225%

    No Known Activations