© 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. 14892
    Prev
    Next
    INDEX
    Explanations

    words related to disbelief, disgust, and disrespect

    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
    866
    +0.14
    0.5%
    1535
    +0.10
    0.3%
    501
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    866
    +0.14
    0.03
    765
    +0.10
    0.03
    501
    +0.10
    0.03
    Negative Logits
     on
    -0.71
     to
    -0.66
     Rome
    -0.63
     in
    -0.63
     for
    -0.62
     
    -0.61
     of
    -0.60
     has
    -0.59
     or
    -0.59
    ,
    -0.59
    POSITIVE LOGITS
     dises
    1.75
    fordable
    1.47
     fatis
    1.37
     hdi
    1.37
     fta
    1.37
     isuzu
    1.33
     ftu
    1.32
     dci
    1.32
     imbal
    1.32
     milano
    1.31
    Activations Density 0.045%

    No Known Activations