© 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. 6154
    Prev
    Next
    INDEX
    Explanations

    mentions of political activists

    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
    1870
    +0.17
    0.6%
    314
    +0.14
    0.5%
    871
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.17
    0.02
    325
    +0.14
    0.03
    1865
    +0.12
    0.02
    Negative Logits
    unhofer
    -0.48
     chì
    -0.47
     iman
    -0.46
    Gos
    -0.46
     nunc
    -0.45
     CreateTagHelper
    -0.45
     autorytatywna
    -0.45
     dó
    -0.44
     nakalista
    -0.44
    OGND
    -0.44
    POSITIVE LOGITS
     activists
    1.13
     activist
    1.11
     Activ
    1.03
     activism
    1.02
    Activ
    0.83
     getActivity
    0.81
     Acti
    0.81
     gaily
    0.79
     activ
    0.79
    activ
    0.78
    Activations Density 0.074%

    No Known Activations