© 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. 5164
    Prev
    Next
    INDEX
    Explanations

    text related to image captions in news articles

    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
    544
    +0.17
    0.6%
    1150
    +0.15
    0.5%
    1895
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1895
    +0.17
    0.03
    544
    +0.15
    0.03
    1376
    +0.14
    0.02
    Negative Logits
     Arce
    -0.62
     armon
    -0.61
     fuit
    -0.60
     Guel
    -0.60
     Gij
    -0.59
     gallina
    -0.59
     disting
    -0.57
     democra
    -0.57
     Palest
    -0.55
     folle
    -0.55
    POSITIVE LOGITS
     caption
    1.26
     captions
    1.11
    caption
    1.05
     Caption
    1.03
     Captions
    0.96
    Caption
    0.94
     captioned
    0.86
    CAPTION
    0.68
     description
    0.53
     frumos
    0.51
    Activations Density 0.045%

    No Known Activations