© 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. 6-RES-JB
    11. 2861
    Prev
    Next
    INDEX
    Explanations

    phrases related to relaxation and leisure activities

    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
    +0.26
    1.0%
    1013
    +0.17
    0.6%
    369
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.26
    0.13
    51
    +0.17
    0.03
    1706
    +0.10
    0.06
    Negative Logits
    <bos>
    -2.29
    Descripció
    -0.65
    webElementXpaths
    -0.64
    public
    -0.63
     asked
    -0.59
    trans
    -0.58
    ask
    -0.56
     ask
    -0.56
    System
    -0.56
    echo
    -0.56
    POSITIVE LOGITS
     swarovski
    1.52
     lele
    1.39
     bandung
    1.39
     tricot
    1.38
     maneu
    1.38
     lyon
    1.37
     impra
    1.35
     wien
    1.35
     aen
    1.35
     reft
    1.34
    Activations Density 1.528%

    No Known Activations