© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1869
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Bri" followed by a number from 8 to 10

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    122
    +0.10
    0.3%
    1492
    +0.10
    0.3%
    1035
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.03
    1343
    +0.10
    0.03
    1335
    +0.08
    0.02
    Negative Logits
    <
    -0.70
                
    -0.69
     толкова
    -0.69
    ะ
    -0.68
     have
    -0.67
    就
    -0.67
    ่า
    -0.67
     стра
    -0.67
    ,
    -0.67
    text
    -0.66
    POSITIVE LOGITS
     Bri
    2.41
     maneu
    2.36
    Bri
    2.15
     increa
    2.15
     affor
    2.15
     excru
    2.11
     wien
    2.08
     strick
    2.05
     emphat
    2.01
     scrat
    2.00
    Activations Density 0.181%

    No Known Activations