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. 6793
    Prev
    Next
    INDEX
    Explanations

    phrases related to contests and submission deadlines

    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
    +0.29
    1.0%
    2034
    +0.11
    0.4%
    453
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    856
    +0.29
    0.03
    1088
    +0.11
    0.03
    776
    +0.09
    0.04
    Negative Logits
    <bos>
    -2.61
    glTranslatef
    -0.65
    addLast
    -0.64
    glLoadIdentity
    -0.63
     prosper
    -0.61
     emerge
    -0.60
     attend
    -0.59
     rehabilitate
    -0.58
    <tfoot>
    -0.58
     AssemblyTitle
    -0.57
    POSITIVE LOGITS
     lele
    1.68
     Minang
    1.63
     Keny
    1.58
     maneu
    1.58
     bandung
    1.55
     saar
    1.54
     hcm
    1.49
     jaya
    1.43
     Pekan
    1.41
     bayern
    1.41
    Activations Density 0.229%

    No Known Activations