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. 8428
    Prev
    Next
    INDEX
    Explanations

    words related to legal or bureaucratic processes

    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
    +0.23
    0.8%
    1741
    +0.14
    0.5%
    1445
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1406
    +0.23
    0.05
    1950
    +0.14
    0.05
    1445
    +0.13
    0.06
    Negative Logits
     bourgeo
    -1.31
     sappi
    -1.31
     applau
    -1.26
     incess
    -1.26
     igno
    -1.17
     nutr
    -1.13
     emphat
    -1.12
     ordina
    -1.12
    ;;)
    -1.11
     simplif
    -1.10
    POSITIVE LOGITS
     there
    0.78
     although
    0.73
     it
    0.70
     while
    0.69
     we
    0.66
     they
    0.64
     the
    0.61
     if
    0.61
     despite
    0.60
     since
    0.60
    Activations Density 0.245%

    No Known Activations