© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 14910
    Prev
    Next
    INDEX
    Explanations

    racial and ethnic terms in a discussion context

    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
    1870
    +0.15
    0.5%
    521
    +0.13
    0.4%
    1101
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    521
    +0.15
    0.03
    1101
    +0.13
    0.02
    1520
    +0.11
    0.02
    Negative Logits
    Nuorodos
    -0.60
    ApiProperty
    -0.55
    Lugares
    -0.49
     itinéraires
    -0.47
    Referencies
    -0.47
    Història
    -0.47
    })+\
    -0.46
     Bauch
    -0.46
    Unmount
    -0.46
    JoinTable
    -0.46
    POSITIVE LOGITS
     Augu
    1.15
     racial
    1.11
     Racial
    1.06
     Mlle
    0.96
     Telex
    0.96
     fta
    0.95
     cartier
    0.94
     Motos
    0.94
     ftu
    0.94
     paff
    0.93
    Activations Density 0.041%

    No Known Activations