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. 419
    Prev
    Next
    INDEX
    Explanations

    numerical values occurring in text

    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
    381
    +0.13
    0.4%
    1967
    +0.12
    0.4%
    687
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    528
    +0.13
    0.04
    1967
    +0.12
    0.04
    1990
    +0.12
    0.04
    Negative Logits
     womit
    -0.71
     weshalb
    -0.69
     wodurch
    -0.68
     worauf
    -0.67
     dachshund
    -0.64
     dziecko
    -0.59
     zumal
    -0.58
     nadzie
    -0.57
     wicker
    -0.56
     wspania
    -0.55
    POSITIVE LOGITS
     utop
    1.26
     incess
    1.19
     vogli
    1.14
     solidar
    1.12
     sappi
    1.12
     republi
    1.11
     apparti
    1.11
     ritard
    1.09
     alkoh
    1.09
     allarg
    1.07
    Activations Density 0.191%

    No Known Activations