© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3784
    Prev
    Next
    INDEX
    Explanations

    expressions related to recurring themes or topics

    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
    1034
    +0.11
    0.4%
    411
    +0.10
    0.4%
    1276
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1034
    +0.11
    0.02
    1276
    +0.10
    0.02
    1705
    +0.10
    0.02
    Negative Logits
     uhr
    -0.83
     lele
    -0.77
     siff
    -0.74
     papi
    -0.74
     abr
    -0.71
     prodi
    -0.69
     makro
    -0.67
     lemp
    -0.66
     kram
    -0.66
     utop
    -0.66
    POSITIVE LOGITS
     theme
    1.44
    theme
    1.32
     Theme
    1.30
     themes
    1.26
    Theme
    1.24
     THEME
    1.16
    THEME
    1.11
     Themes
    1.09
    themes
    1.08
    Themes
    1.00
    Activations Density 0.075%

    No Known Activations