© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4293
    Prev
    Next
    INDEX
    Explanations

    articles related to political movements, actions, and individuals

    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
    1150
    +0.16
    0.5%
    2034
    +0.14
    0.4%
    468
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1354
    +0.16
    0.06
    1220
    +0.14
    0.04
    1150
    +0.13
    0.03
    Negative Logits
    Glej
    -0.66
    Več
    -0.66
    "]))
    -0.64
    Wię
    -0.63
    ())))
    -0.62
    Eksteraj
    -0.62
    Legături
    -0.59
    ']));
    -0.59
    Prí
    -0.58
    Izvori
    -0.57
    POSITIVE LOGITS
     fch
    1.16
     embra
    1.15
     idr
    1.14
     franz
    1.14
     tremb
    1.10
     vns
    1.10
     sii
    1.09
     effe
    1.09
     suscep
    1.08
     unil
    1.08
    Activations Density 0.323%

    No Known Activations