© 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. 1477
    Prev
    Next
    INDEX
    Explanations

    phrases related to wishing good luck

    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
    437
    +0.07
    0.2%
    1839
    +0.07
    0.2%
    47
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    15
    +0.07
    0.02
    1954
    +0.07
    0.02
    94
    +0.06
    0.02
    Negative Logits
    /***
    -0.63
    hold
    -0.60
     hold
    -0.57
    public
    -0.57
    big
    -0.55
     serve
    -0.55
    大
    -0.53
    invoke
    -0.52
     expose
    -0.52
     asked
    -0.52
    POSITIVE LOGITS
     luck
    2.17
     Luck
    1.64
    Luck
    1.53
    luck
    1.42
     LUCK
    1.37
     cabrio
    1.19
    LUCK
    1.19
     sappi
    1.15
     carrefour
    1.14
    capulco
    1.14
    Activations Density 0.106%

    No Known Activations