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. 15288
    Prev
    Next
    INDEX
    Explanations

    quotations and words with special characters (such as quotation marks and slashes)

    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
    2019
    +0.16
    0.5%
    736
    +0.12
    0.3%
    50
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.16
    0.04
    545
    +0.12
    0.03
    1541
    +0.09
    0.03
    Negative Logits
     impra
    -1.78
     snoopy
    -1.75
     reluct
    -1.74
     strick
    -1.72
     increa
    -1.72
     depic
    -1.71
     scrat
    -1.70
     secon
    -1.68
     shenan
    -1.66
     disagre
    -1.65
    POSITIVE LOGITS
    BoxShadow
    0.81
    MouseAdapter
    0.80
     سكانية
    0.71
    astify
    0.70
    Trotz
    0.70
     ideolog
    0.70
    bibfnamefont
    0.68
     nueces
    0.66
     nasel
    0.66
    TextInputLayout
    0.65
    Activations Density 0.167%

    No Known Activations