© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 11421
    Prev
    Next
    INDEX
    Explanations

    phrases related to job/career roles and hierarchy

    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
    453
    +0.09
    0.3%
    227
    +0.09
    0.2%
    478
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1659
    +0.09
    0.04
    232
    +0.09
    0.04
    474
    +0.08
    0.03
    Negative Logits
     thut
    -1.65
     effe
    -1.64
     fta
    -1.60
     fte
    -1.56
     maneu
    -1.56
     strick
    -1.52
     secon
    -1.51
     fto
    -1.50
     unce
    -1.50
     ftu
    -1.50
    POSITIVE LOGITS
    <bos>
    1.00
     favorite
    0.69
     closest
    0.64
     biggest
    0.62
     partner
    0.60
     own
    0.60
     nearest
    0.59
     favourite
    0.59
     sole
    0.57
     counterpart
    0.57
    Activations Density 0.197%

    No Known Activations