© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2628
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Daddy" in contexts such as family relationships, childhood memories, and character interactions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1306
    +0.10
    0.3%
    662
    +0.09
    0.3%
    484
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    823
    +0.10
    0.03
    1363
    +0.09
    0.02
    1343
    +0.08
    0.03
    Negative Logits
     underval
    -0.67
     harmonize
    -0.66
     intersper
    -0.65
    Bullshit
    -0.63
    TheGreat
    -0.62
     unify
    -0.61
     rouse
    -0.60
     disbur
    -0.58
    ⓧ
    -0.57
     krishna
    -0.57
    POSITIVE LOGITS
     Daddy
    2.11
     daddy
    2.03
    Daddy
    1.86
    daddy
    1.68
     Mommy
    1.67
     mommy
    1.61
    Mommy
    1.40
    mommy
    1.19
     Mummy
    1.08
     mummy
    1.01
    Activations Density 0.253%

    No Known Activations