© 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. 5161
    Prev
    Next
    INDEX
    Explanations

    phrases related to persuasive speeches or promises

    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
    382
    +0.15
    0.4%
    394
    +0.13
    0.4%
    1741
    +0.12
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.15
    0.07
    736
    +0.13
    0.07
    394
    +0.12
    0.05
    Negative Logits
     alkoh
    -1.43
     meras
    -1.40
     antik
    -1.38
     makro
    -1.38
     istan
    -1.36
     thuy
    -1.35
     ù
    -1.35
     parati
    -1.33
     luy
    -1.32
     valla
    -1.31
    POSITIVE LOGITS
     yes
    0.81
     no
    0.78
     yeah
    0.71
    Cześć
    0.71
     huh
    0.70
     maybe
    0.67
     nothing
    0.63
     always
    0.62
     așa
    0.61
    Einen
    0.61
    Activations Density 0.403%

    No Known Activations