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. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14053
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "race"

    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
    521
    +0.18
    0.7%
    555
    +0.17
    0.7%
    1407
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.18
    0.04
    555
    +0.17
    0.03
    1407
    +0.15
    0.03
    Negative Logits
    々木
    -0.50
     pí
    -0.49
     piatta
    -0.49
    Horário
    -0.47
     didat
    -0.46
     svolge
    -0.46
    Jennifer
    -0.45
    plein
    -0.45
     vostre
    -0.45
    quido
    -0.44
    POSITIVE LOGITS
     race
    1.34
     Race
    1.26
     RACE
    1.24
    Race
    1.20
     races
    1.12
     hairc
    1.10
     Races
    1.09
    race
    1.09
     ecru
    1.09
     gaily
    1.07
    Activations Density 0.037%

    No Known Activations