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. 6814
    Prev
    Next
    INDEX
    Explanations

    details related to prices and dates

    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
    1343
    +0.20
    0.8%
    1177
    +0.16
    0.6%
    50
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.20
    0.12
    1343
    +0.16
    0.12
    1177
    +0.15
    0.03
    Negative Logits
    <bos>
    -3.56
    <?
    -0.86
     onPostExecute
    -0.80
    archiviato
    -0.75
    /**
    -0.75
    .
    -0.74
     viewWillAppear
    -0.73
    ⓧ
    -0.73
    },[])
    -0.72
     információk
    -0.72
    POSITIVE LOGITS
     practition
    1.89
     accla
    1.88
     emphat
    1.86
     volunte
    1.85
     quelquefois
    1.81
     resear
    1.80
     sergio
    1.79
     wikihow
    1.76
     véhic
    1.72
     quoique
    1.71
    Activations Density 1.009%

    No Known Activations