© 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. 5428
    Prev
    Next
    INDEX
    Explanations

    instances of the word "sit" in different contexts

    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
    +0.18
    1.0%
    1671
    +0.12
    0.7%
    1045
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.18
    0.03
    1045
    +0.12
    0.03
    1323
    +0.10
    0.03
    Negative Logits
    <bos>
    -2.95
    /***
    -0.66
    РЭ
    -0.60
    verifyException
    -0.56
    public
    -0.56
     gynnwys
    -0.55
    Vegeu
    -0.54
    /***
    -0.53
    //};
    -0.53
     declare
    -0.53
    POSITIVE LOGITS
     lidl
    1.10
     unlaw
    1.10
     stockholm
    1.07
    dirond
    1.06
     pollut
    1.05
     disreg
    1.05
     fortn
    1.05
     despotism
    1.03
     maneu
    1.01
     Sitting
    1.01
    Activations Density 0.099%

    No Known Activations