© 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. 14931
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to political candidates and events

    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
    453
    +0.16
    0.5%
    184
    +0.16
    0.5%
    764
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.16
    0.02
    184
    +0.16
    0.01
    137
    +0.15
    0.01
    Negative Logits
    ьаж
    -0.89
     Roskov
    -0.59
    ыгана
    -0.57
     Exacts
    -0.57
    >--}}
    -0.53
    UnsafeEnabled
    -0.52
    blurRadius
    -0.51
     calendriers
    -0.51
     Paglinawan
    -0.51
     vairāk
    -0.49
    POSITIVE LOGITS
     reluct
    1.40
     affor
    1.39
     indestru
    1.32
     impra
    1.24
     increa
    1.21
     depic
    1.20
     shenan
    1.19
     philanth
    1.18
     inconce
    1.17
     unve
    1.14
    Activations Density 0.024%

    No Known Activations