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. 412
    Prev
    Next
    INDEX
    Explanations

    past tense verbs related to physical activities or movements

    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
    47
    +0.13
    0.4%
    410
    +0.12
    0.4%
    555
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.13
    0.05
    410
    +0.12
    0.04
    1993
    +0.11
    0.05
    Negative Logits
    JsonFormat
    -0.54
    HasColumnName
    -0.54
    geslacht
    -0.50
    PathParam
    -0.47
    Discografia
    -0.46
    usstsein
    -0.46
    QWidget
    -0.45
    Decomposition
    -0.45
     Frucht
    -0.45
    bulos
    -0.44
    POSITIVE LOGITS
     increa
    1.37
     intersper
    1.26
     unden
    1.25
     RUNNING
    1.23
     affor
    1.22
     nutella
    1.21
     encomp
    1.21
     swarovski
    1.20
     run
    1.14
     scrat
    1.14
    Activations Density 0.106%

    No Known Activations