© 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. 4969
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals and their actions or statements

    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
    856
    +0.15
    0.5%
    381
    +0.13
    0.4%
    1445
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1288
    +0.15
    0.05
    946
    +0.13
    0.03
    776
    +0.12
    0.04
    Negative Logits
     tricot
    -1.26
     ecru
    -1.17
     swarovski
    -0.98
     velour
    -0.98
     amigurumi
    -0.97
     embodi
    -0.97
     tupperware
    -0.96
     hairc
    -0.94
     thermomix
    -0.91
     fusible
    -0.86
    POSITIVE LOGITS
     panik
    0.97
     kompati
    0.93
    IsContent
    0.92
     indik
    0.90
     kemer
    0.90
     akut
    0.90
     maksi
    0.89
     praktik
    0.89
    MessageOf
    0.87
     induk
    0.87
    Activations Density 0.188%

    No Known Activations