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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2058
    Prev
    Next
    INDEX
    Explanations

    mentions of characters with disabilities and their portrayal in different adaptations

    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
    198
    +0.14
    0.4%
    381
    +0.10
    0.3%
    876
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.05
    908
    +0.10
    0.02
    1980
    +0.09
    0.02
    Negative Logits
     électron
    -0.46
     caractéris
    -0.46
    banyak
    -0.45
     refroid
    -0.44
     écou
    -0.42
    kenal
    -0.42
    ıll
    -0.42
    oltán
    -0.41
     Ancho
    -0.41
    Népesség
    -0.41
    POSITIVE LOGITS
    nemia
    0.71
    UAWEI
    0.66
    astéro
    0.65
     meis
    0.61
     ovale
    0.61
     moza
    0.60
     koch
    0.60
     tev
    0.60
     Hvad
    0.60
     Væ
    0.59
    Activations Density 0.545%

    No Known Activations