© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1938
    Prev
    Next
    INDEX
    Explanations

    phrases related to the release or publishing of 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
    678
    +0.16
    0.5%
    1150
    +0.14
    0.4%
    776
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.16
    0.08
    16
    +0.14
    0.06
    1907
    +0.09
    0.04
    Negative Logits
     nutella
    -0.85
     ecru
    -0.79
     tupperware
    -0.77
     swarovski
    -0.75
     gilet
    -0.72
     hoody
    -0.71
     bologna
    -0.69
     cushi
    -0.67
     hairc
    -0.66
     Quinoa
    -0.64
    POSITIVE LOGITS
     photos
    0.73
     photographs
    0.72
     images
    0.72
     pictures
    0.71
     screenshots
    0.66
     NKC
    0.64
     vediamo
    0.64
     information
    0.64
     footage
    0.63
     notor
    0.63
    Activations Density 0.510%

    No Known Activations