© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1646
    Prev
    Next
    INDEX
    Explanations

    references to nudity

    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
    874
    +0.09
    0.3%
    498
    +0.09
    0.2%
    2011
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.09
    0.03
    1363
    +0.09
    0.02
    1935
    +0.08
    0.02
    Negative Logits
     assiste
    -0.71
     Châ
    -0.71
     vola
    -0.64
    <bos>
    -0.62
     Mâ
    -0.61
     brille
    -0.59
     contribue
    -0.59
     apparti
    -0.58
     doman
    -0.58
     Parigi
    -0.58
    POSITIVE LOGITS
     nude
    2.31
     Nude
    1.81
    nude
    1.54
     nudity
    1.09
     ingrat
    1.01
     unwarran
    0.91
     disagre
    0.86
     balenciaga
    0.85
     vainly
    0.82
     unspeak
    0.82
    Activations Density 0.304%

    No Known Activations