© 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. 4955
    Prev
    Next
    INDEX
    Explanations

    words related to social issues and political protests

    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
    764
    +0.18
    0.6%
    856
    +0.17
    0.5%
    906
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    764
    +0.18
    0.06
    856
    +0.17
    0.04
    1842
    +0.14
    0.04
    Negative Logits
     Paglinawan
    -1.10
    Sqft
    -0.98
    Espèce
    -0.97
    IsContent
    -0.92
     كومونز
    -0.90
    Erreferentziak
    -0.90
     Walkover
    -0.89
    UnusedPrivate
    -0.86
    Legături
    -0.86
    Palmar
    -0.83
    POSITIVE LOGITS
     encomp
    2.34
     affor
    2.24
     maneu
    2.22
     increa
    2.22
     disagre
    2.21
     hairc
    2.19
     impra
    2.18
     suscep
    2.17
     guarante
    2.15
     reluct
    2.15
    Activations Density 0.411%

    No Known Activations