© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5217
    Prev
    Next
    INDEX
    Explanations

    mentions of suffering or related terms

    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
    +0.15
    0.9%
    1828
    +0.11
    0.6%
    1806
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1174
    +0.15
    0.03
    630
    +0.11
    0.03
    25
    +0.10
    0.03
    Negative Logits
    <bos>
    -3.79
    public
    -0.97
    HasIndex
    -0.90
    ;
    -0.89
    .
    -0.89
    CreateIndex
    -0.88
    hline
    -0.88
    item
    -0.88
    struct
    -0.87
    BUYER
    -0.87
    POSITIVE LOGITS
     affor
    3.08
     stockholm
    3.01
     increa
    3.00
     maneu
    2.89
     impra
    2.88
     strick
    2.85
     fta
    2.81
     madonna
    2.78
     depic
    2.76
     scrat
    2.74
    Activations Density 0.125%

    No Known Activations