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. 1063
    Prev
    Next
    INDEX
    Explanations

    intense adjectives indicating seriousness or significance

    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
    +0.27
    1.1%
    1385
    +0.12
    0.5%
    678
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.27
    0.08
    1904
    +0.12
    0.07
    678
    +0.10
    0.07
    Negative Logits
    <bos>
    -2.55
    HttpPut
    -0.78
     modalités
    -0.76
     finally
    -0.75
     prochaines
    -0.73
     procédures
    -0.72
    IEnumerator
    -0.72
    HttpDelete
    -0.72
     négociations
    -0.71
    ⓧ
    -0.70
    POSITIVE LOGITS
     riva
    1.60
     Minang
    1.58
     bandung
    1.54
     jaya
    1.53
    postolic
    1.52
     hcm
    1.47
     jati
    1.45
     tramont
    1.45
     quoc
    1.43
     mosso
    1.43
    Activations Density 0.543%

    No Known Activations