© 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 EvalsExportsinterp-engineNEWAPI 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. 15200
    Prev
    Next
    INDEX
    Explanations

    references to community engagement, political activities, and social issues

    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
    1842
    +0.17
    0.5%
    1343
    +0.15
    0.5%
    394
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    394
    +0.17
    0.08
    1261
    +0.15
    0.02
    609
    +0.14
    0.06
    Negative Logits
     cytoplas
    -0.65
    throwaway
    -0.60
    Quantification
    -0.55
     logarith
    -0.53
     constamment
    -0.50
     frow
    -0.50
    Opportun
    -0.50
     razer
    -0.50
     дописавши
    -0.49
     aussitôt
    -0.49
    POSITIVE LOGITS
    []"
    0.86
    ").
    0.71
    ”)
    0.71
    ”).
    0.70
    ”
    0.68
    ")
    0.67
    ”,
    0.65
    "),
    0.65
    ”),
    0.64
    ”:
    0.64
    Activations Density 1.036%

    No Known Activations