© 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 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. 10748
    Prev
    Next
    INDEX
    Explanations

    racial and ethnic descriptors based on the context of the sentence, especially related to white and black individuals

    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%
    1385
    +0.11
    0.3%
    825
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.14
    0.05
    1124
    +0.11
    0.04
    1404
    +0.11
    0.04
    Negative Logits
    FormTagHelper
    -0.58
     gynhyrchwyd
    -0.51
    RenderAtEndOf
    -0.50
    glTexCoord
    -0.46
    RectF
    -0.46
    Referencoj
    -0.45
    FormState
    -0.45
    positorio
    -0.44
    InputTagHelper
    -0.44
    InitStructure
    -0.44
    POSITIVE LOGITS
     Áng
    1.10
     Darío
    0.91
     cartier
    0.89
     Juf
    0.86
     Joaqu
    0.84
     Augu
    0.84
     Souha
    0.81
     Châ
    0.81
     Mónica
    0.80
     Sinal
    0.80
    Activations Density 0.159%

    No Known Activations