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. 8220
    Prev
    Next
    INDEX
    Explanations

    terminology related to scientific theories and methods

    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
    872
    +0.21
    0.6%
    1253
    +0.12
    0.4%
    203
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.21
    0.08
    203
    +0.12
    0.04
    563
    +0.09
    0.03
    Negative Logits
    UnusedPrivate
    -0.68
    AddHtmlAttribute
    -0.65
    BeginInit
    -0.64
    EndInit
    -0.63
     ***!
    -0.61
    smithy
    -0.60
    UDAD
    -0.58
    Javadoc
    -0.57
    anglès
    -0.57
    RegressionTest
    -0.57
    POSITIVE LOGITS
     increa
    1.36
     impra
    1.34
     hentai
    1.34
     disreg
    1.34
     milf
    1.32
     maneu
    1.32
     snoopy
    1.31
     shenan
    1.30
     stickied
    1.29
     intersper
    1.28
    Activations Density 0.695%

    No Known Activations