© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 269
    Prev
    Next
    INDEX
    Explanations

    words related to harmful actions or negative impacts on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.10
    0.4%
    513
    +0.10
    0.3%
    442
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1043
    +0.10
    0.07
    416
    +0.10
    0.06
    975
    +0.08
    0.06
    Negative Logits
    <bos>
    -1.81
     endeavored
    -1.43
     endeavouring
    -1.37
     endeavoured
    -1.37
     intersper
    -1.34
     strove
    -1.33
     endow
    -1.30
     chanced
    -1.28
     impelled
    -1.28
     renounced
    -1.26
    POSITIVE LOGITS
    GYPT
    1.29
    nachron
    1.23
     pernic
    1.22
    eronau
    1.20
    jectures
    1.20
    quarelle
    1.18
     trion
    1.17
    pection
    1.16
    dirond
    1.15
     cammin
    1.14
    Activations Density 0.220%

    No Known Activations