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. 983
    Prev
    Next
    INDEX
    Explanations

    words associated with urgent humanitarian issues and refugee situations

    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
    453
    +0.19
    0.6%
    50
    +0.18
    0.6%
    1177
    +0.16
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1330
    +0.19
    0.05
    142
    +0.18
    0.05
    56
    +0.16
    0.04
    Negative Logits
     intersper
    -2.60
     increa
    -2.54
     encomp
    -2.53
     affor
    -2.44
     hairc
    -2.44
     scrat
    -2.42
     indestru
    -2.38
     milf
    -2.37
     swarovski
    -2.35
     emphat
    -2.35
    POSITIVE LOGITS
    <i>
    0.79
    <em>
    0.78
     ***!
    0.78
    <u>
    0.77
    EndInit
    0.76
    UTF
    0.76
    cloudflare
    0.75
    <strong>
    0.75
    <b>
    0.74
    İstinadlar
    0.72
    Activations Density 0.137%

    No Known Activations