© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 7161
    Prev
    Next
    INDEX
    Explanations

    contexts related to coping with challenges or difficult situations

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.14
    0.6%
    690
    +0.12
    0.5%
    303
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.14
    0.07
    166
    +0.12
    0.07
    1183
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.43
    /***
    
    -0.56
     السياسية
    -0.54
    displayquote
    -0.52
    set
    -0.51
     support
    -0.51
     bring
    -0.51
     brings
    -0.51
     enable
    -0.51
    cyklopedia
    -0.51
    POSITIVE LOGITS
     scrat
    1.18
     impra
    1.13
     chré
    1.12
     maneu
    1.12
     pollut
    1.11
     stockholm
    1.10
     fortn
    1.06
     unden
    1.04
     excru
    1.04
     strick
    1.03
    Activations Density 1.191%

    No Known Activations