Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 695
    Prev
    Next
    INDEX
    Explanations

    mentions of jihadist groups and their activities

    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
    +0.24
    0.9%
    1842
    +0.13
    0.5%
    198
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.24
    0.04
    1842
    +0.13
    0.03
    198
    +0.10
    0.05
    Negative Logits
    <bos>
    -3.41
    BeginContext
    -0.69
     createSprite
    -0.68
    IsMutable
    -0.68
    public
    -0.68
     ProtoMessage
    -0.64
     ivelany
    -0.64
    MockBean
    -0.61
    JspWriter
    -0.60
    rungsseite
    -0.60
    POSITIVE LOGITS
     affor
    1.77
     unlaw
    1.68
     increa
    1.62
     unwarran
    1.61
     beaute
    1.61
     reluct
    1.60
     unspeak
    1.60
     tolerably
    1.59
     gaily
    1.57
     impra
    1.52
    Activations Density 0.316%

    No Known Activations