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. 12-RES-JB
    6. 178
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude and appreciation

    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.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.12.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    12
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.48
    1.9%
    776
    +0.10
    0.4%
    630
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.48
    0.23
    1919
    +0.10
    0.14
    1415
    +0.08
    0.14
    Negative Logits
    <bos>
    -1.60
    TagMode
    -0.61
    通販
    -0.57
     also
    -0.56
    GraphicsUnit
    -0.56
    AddTagHelper
    -0.54
    Koordinaten
    -0.53
    also
    -0.53
    ┣
    -0.53
    )-
    -0.52
    POSITIVE LOGITS
     Keny
    1.44
     McLaugh
    1.37
     Bartholo
    1.34
     Juf
    1.32
     unlaw
    1.28
     Jusqu
    1.27
     Haci
    1.26
     McInt
    1.22
     pamph
    1.22
     Rine
    1.21
    Activations Density 9.605%

    No Known Activations