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. 1858
    Prev
    Next
    INDEX
    Explanations

    references to time or actions taken in a political or legal context

    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
    +0.21
    0.7%
    596
    +0.09
    0.3%
    2031
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2031
    +0.21
    0.08
    1493
    +0.09
    0.08
    1561
    +0.06
    0.08
    Negative Logits
    <bos>
    -2.12
    +#+
    -0.69
    ysacchar
    -0.65
    glLoadIdentity
    -0.65
    endmodule
    -0.61
    Geplaatst
    -0.61
     trattano
    -0.61
    glTexCoord
    -0.60
    glTex
    -0.58
    AsUp
    -0.57
    POSITIVE LOGITS
     disagre
    1.13
     shenan
    1.12
     apprehen
    1.07
     Darío
    1.06
     unwarran
    1.05
     impra
    1.03
     maneu
    1.01
     unlaw
    1.01
     milf
    1.00
     lidl
    0.99
    Activations Density 2.238%

    No Known Activations