© 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. 11777
    Prev
    Next
    INDEX
    Explanations

    names and terms related to political figures and actions

    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
    314
    +0.20
    0.8%
    410
    +0.14
    0.6%
    1323
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.20
    0.07
    314
    +0.14
    0.04
    410
    +0.13
    0.05
    Negative Logits
     tawny
    -0.65
     unspeak
    -0.56
     quartzite
    -0.54
    orsche
    -0.53
     friable
    -0.53
     wrink
    -0.53
     ruddy
    -0.52
     chaste
    -0.50
     linseed
    -0.50
     pinkish
    -0.50
    POSITIVE LOGITS
    Dol
    0.74
     eccl
    0.73
    Bol
    0.70
    Tol
    0.70
     Bol
    0.69
     inol
    0.69
    Jol
    0.68
     adal
    0.67
     protokol
    0.66
     Nol
    0.66
    Activations Density 0.366%

    No Known Activations