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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 8458
    Prev
    Next
    INDEX
    Explanations

    descriptions of locations and views

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    906
    +0.13
    0.4%
    1385
    +0.11
    0.3%
    1013
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1804
    +0.13
    0.03
    906
    +0.11
    0.00
    289
    +0.10
    0.01
    Negative Logits
     panik
    -0.84
     kram
    -0.84
     maksi
    -0.83
     kado
    -0.82
     Souha
    -0.79
     jaya
    -0.78
     seksi
    -0.77
     praktik
    -0.74
     jorge
    -0.74
     alberto
    -0.69
    POSITIVE LOGITS
     views
    0.88
     view
    0.80
     panoramic
    0.79
     overlooking
    0.78
     Views
    0.75
     VIEWS
    0.72
    views
    0.67
    Views
    0.65
     View
    0.64
    view
    0.60
    Activations Density 0.194%

    No Known Activations