© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    references to fate, destiny, and predetermined events

    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
    1044
    +0.11
    0.4%
    67
    +0.10
    0.4%
    50
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    596
    +0.11
    0.02
    636
    +0.10
    0.02
    1044
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.09
    register
    -0.63
    app
    -0.59
     maintain
    -0.58
    arr
    -0.58
    hyper
    -0.58
    layer
    -0.57
    riwal
    -0.57
    Layer
    -0.56
    public
    -0.56
    POSITIVE LOGITS
     mcdonald
    1.23
     fate
    1.23
     stockholm
    1.18
     Fate
    1.15
     casio
    1.15
     destiny
    1.14
    Fate
    1.13
     dises
    1.13
     mercu
    1.10
     fates
    1.09
    Activations Density 0.235%

    No Known Activations