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. 8262
    Prev
    Next
    INDEX
    Explanations

    expressions related to financial cost, fear of change, and discussions about the best option

    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
    1253
    +0.14
    0.4%
    1978
    +0.12
    0.4%
    674
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    875
    +0.14
    0.03
    942
    +0.12
    0.06
    1176
    +0.11
    0.02
    Negative Logits
     fte
    -1.05
     „,
    -1.02
     tew
    -1.00
     profi
    -1.00
     inder
    -0.99
     bett
    -0.98
     fto
    -0.98
     secon
    -0.98
     laun
    -0.98
     wien
    -0.96
    POSITIVE LOGITS
     etc
    0.57
     somehow
    0.57
    LEGGI
    0.56
    setDisabled
    0.54
    ēju
    0.52
    ביוגרפיה
    0.52
    etc
    0.51
    MIDDLEWARE
    0.50
    توضیحات
    0.50
    wohnung
    0.49
    Activations Density 0.922%

    No Known Activations