© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1273
    Prev
    Next
    INDEX
    Explanations

    references to vegan recipes and vegan lifestyle

    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
    1974
    +0.17
    0.8%
    528
    +0.16
    0.7%
    555
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1896
    +0.17
    0.03
    1974
    +0.16
    0.03
    1013
    +0.12
    0.05
    Negative Logits
    <bos>
    -1.28
    +#+#
    -0.61
    @
    -0.60
    rungsseite
    -0.60
    commons
    -0.58
    March
    -0.58
    namespace
    -0.58
     Bor
    -0.57
    Bor
    -0.57
    lelő
    -0.56
    POSITIVE LOGITS
     increa
    1.37
     pollut
    1.32
     ftu
    1.30
     affor
    1.27
     secon
    1.27
     unce
    1.27
     reluct
    1.27
     shenan
    1.26
     unve
    1.26
     fortn
    1.25
    Activations Density 0.528%

    No Known Activations