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. 1464
    Prev
    Next
    INDEX
    Explanations

    phrases or excerpts related to religious transformation or missionary work, including giving reasons for hope

    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
    1842
    +0.17
    0.5%
    1253
    +0.15
    0.5%
    453
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    185
    +0.17
    0.03
    1446
    +0.15
    0.03
    1380
    +0.15
    0.02
    Negative Logits
     due
    -0.71
     de
    -0.70
     שלנו
    -0.70
     no
    -0.68
     so
    -0.68
     too
    -0.68
     on
    -0.68
     fix
    -0.67
    drawLine
    -0.67
     extra
    -0.66
    POSITIVE LOGITS
     wien
    2.39
     inder
    2.33
     effe
    2.32
     noel
    2.31
     stockholm
    2.29
     oner
    2.18
     lidl
    2.16
     bett
    2.15
     dispen
    2.15
     franz
    2.14
    Activations Density 0.091%

    No Known Activations