© 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. 1298
    Prev
    Next
    INDEX
    Explanations

    phrases related to human interactions or descriptions of scenes involving people

    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
    50
    +0.13
    0.5%
    1108
    +0.08
    0.3%
    2019
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    50
    +0.13
    0.09
    2019
    +0.08
    0.10
    1288
    +0.07
    0.04
    Negative Logits
    <bos>
    -1.20
    ⓧ
    -0.87
    TextAppearance
    -0.84
            
    -0.79
        
    -0.78
    {
    -0.77
    toMatch
    -0.77
                
    -0.77
    -0.76
    smarty
    -0.76
    POSITIVE LOGITS
     maneu
    3.38
     affor
    3.16
     shenan
    3.16
     increa
    3.13
     disagre
    3.08
     reluct
    3.08
     depic
    3.06
     accla
    3.00
     impra
    2.96
     disreg
    2.91
    Activations Density 1.867%
    No Known Activations