© 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 EvalsExportsinterp-engineNEWAPI 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. 10605
    Prev
    Next
    INDEX
    Explanations

    personal pronouns in possessive form

    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
    776
    +0.16
    0.5%
    478
    +0.13
    0.4%
    1081
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.16
    0.06
    131
    +0.13
    0.04
    1081
    +0.11
    0.07
    Negative Logits
    styleType
    -0.66
     krep
    -0.61
     ļ
    -0.60
     naer
    -0.59
    ==="
    -0.58
     kamb
    -0.58
     polegadas
    -0.57
     saad
    -0.57
     tunn
    -0.57
     papild
    -0.56
    POSITIVE LOGITS
     own
    0.85
    Ehh
    0.67
    Ummm
    0.64
    FTFY
    0.62
    Mhm
    0.62
    Fuckin
    0.59
    Uhh
    0.59
     prouve
    0.56
    YMMV
    0.56
    Uhm
    0.56
    Activations Density 0.369%

    No Known Activations