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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 13985
    Prev
    Next
    INDEX
    Explanations

    mentions of LGBTQ+ related terms and discrimination issues

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    468
    +0.11
    0.3%
    513
    +0.10
    0.3%
    1843
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.11
    0.02
    513
    +0.10
    0.03
    1241
    +0.09
    0.04
    Negative Logits
     corrom
    -0.54
     huma
    -0.49
     dépens
    -0.48
     engend
    -0.48
     peup
    -0.47
    CodedInputStream
    -0.46
     vulga
    -0.45
     dépass
    -0.45
     répand
    -0.45
     palab
    -0.44
    POSITIVE LOGITS
     trecut
    0.58
     dă
    0.54
     disambiguazione
    0.52
     Audiodateien
    0.51
     blest
    0.51
    SBATCH
    0.51
    üedad
    0.50
     împre
    0.49
    jectures
    0.49
     disqual
    0.49
    Activations Density 0.394%

    No Known Activations