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. 15844
    Prev
    Next
    INDEX
    Explanations

    mentions of viewing and files in a technical or organizational context

    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
    674
    +0.09
    0.3%
    1380
    +0.09
    0.3%
    2011
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1524
    +0.09
    0.02
    1036
    +0.09
    0.00
    184
    +0.08
    0.01
    Negative Logits
     purtroppo
    -1.45
     solidar
    -1.40
     utop
    -1.33
     perciò
    -1.28
     ideolog
    -1.26
     chiaramente
    -1.25
     poichè
    -1.23
     logis
    -1.21
     impon
    -1.20
     anzi
    -1.19
    POSITIVE LOGITS
     in
    1.12
     loveliness
    0.89
     gaily
    0.88
     shenan
    0.87
     disagre
    0.87
     unspeak
    0.87
     Shakspeare
    0.85
     zupeł
    0.83
     withal
    0.83
     avenger
    0.83
    Activations Density 0.148%

    No Known Activations