© 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. 16204
    Prev
    Next
    INDEX
    Explanations

    verbs related to asking questions or seeking information

    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
    11
    +0.17
    0.6%
    201
    +0.15
    0.5%
    1350
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    11
    +0.17
    0.07
    201
    +0.15
    0.05
    196
    +0.11
    0.04
    Negative Logits
     febr
    -0.54
     nabi
    -0.49
     panik
    -0.48
     bunda
    -0.48
     kursi
    -0.47
     zey
    -0.47
    hWnd
    -0.47
    ServerError
    -0.44
    pObj
    -0.44
     kapital
    -0.43
    POSITIVE LOGITS
     ask
    1.25
     Asking
    1.16
     Ask
    1.13
     asked
    1.10
     asking
    1.10
     asks
    1.09
     ASK
    1.09
    asking
    1.07
    asked
    1.06
    Asking
    1.04
    Activations Density 0.103%

    No Known Activations