© 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. 4888
    Prev
    Next
    INDEX
    Explanations

    negations and words related to control and opposition

    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
    604
    +0.08
    0.2%
    1908
    +0.08
    0.2%
    1786
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1424
    +0.08
    0.04
    1851
    +0.08
    0.04
    438
    +0.07
    0.05
    Negative Logits
     disagre
    -1.13
     effe
    -1.07
     greate
    -1.07
     desir
    -1.07
     alre
    -1.05
     fuf
    -1.04
     strick
    -1.03
     impra
    -1.03
     apprehen
    -1.02
     reluct
    -1.00
    POSITIVE LOGITS
     tolerate
    0.55
    Consigli
    0.54
     anymore
    0.54
     compromise
    0.54
     accept
    0.52
    Ottimo
    0.52
    Preparazione
    0.52
    upuesto
    0.49
    OGND
    0.49
     pymysql
    0.48
    Activations Density 0.288%

    No Known Activations