© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 183
    Prev
    Next
    INDEX
    Explanations

    phrases related to discrimination laws and legal compliance

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    650
    +0.08
    0.2%
    1107
    +0.07
    0.2%
    1763
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.03
    1363
    +0.07
    0.07
    690
    +0.07
    0.08
    Negative Logits
    sergio
    -0.78
     authentique
    -0.69
    roberto
    -0.68
    THISDAY
    -0.65
     aussitôt
    -0.63
     Senti
    -0.63
     découv
    -0.62
    Să
    -0.61
    logotipo
    -0.61
    Dimensi
    -0.60
    POSITIVE LOGITS
    ∎
    2.18
    ↩
    1.22
     pessi
    1.19
     banan
    1.17
     kram
    1.13
     ciga
    1.12
     Violon
    1.10
     luxem
    1.10
     bayern
    1.10
     ohr
    1.10
    Activations Density 0.589%

    No Known Activations