© 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. 14767
    Prev
    Next
    INDEX
    Explanations

    phrases containing derogatory language and offensive remarks

    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
    +0.12
    0.3%
    538
    +0.11
    0.3%
    1601
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1601
    +0.12
    0.06
    538
    +0.11
    0.05
    1525
    +0.10
    0.04
    Negative Logits
     vogli
    -0.74
     rispond
    -0.72
     dimenti
    -0.69
     desideri
    -0.67
     trovo
    -0.67
     trovi
    -0.64
     credere
    -0.64
     auguri
    -0.63
     vedi
    -0.63
     voleva
    -0.63
    POSITIVE LOGITS
     insults
    0.67
     insult
    0.60
     insulting
    0.59
     remarks
    0.58
     hurled
    0.56
     remark
    0.53
     verbally
    0.53
     derogatory
    0.51
     uttered
    0.51
     comments
    0.50
    Activations Density 0.435%

    No Known Activations