© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 3351
    Prev
    Next
    INDEX
    Explanations

    words related to financial misconduct and ethical violations

    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
    1967
    +0.34
    1.5%
    1842
    +0.26
    1.2%
    50
    +0.19
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1967
    +0.34
    0.17
    1842
    +0.26
    0.07
    198
    +0.19
    0.14
    Negative Logits
    <bos>
    -2.30
     intersper
    -0.76
    isContained
    -0.68
     stik
    -0.66
     zove
    -0.66
     habet
    -0.64
    @[+][
    -0.63
     eorum
    -0.63
     tille
    -0.61
     :)))
    -0.61
    POSITIVE LOGITS
     Muhamma
    0.70
     Bahía
    0.68
     Khart
    0.68
     Palembang
    0.67
     preparare
    0.67
     epoca
    0.66
     barcelona
    0.65
     Coim
    0.65
     Pasir
    0.64
     Kese
    0.64
    Activations Density 3.837%

    No Known Activations