© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3537
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitional expressions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Neuron Alignment
    Index
    Value
    % of L₁
    674
    +0.13
    0.4%
    1504
    +0.08
    0.2%
    468
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1504
    +0.13
    0.03
    1808
    +0.08
    0.02
    1830
    +0.07
    0.02
    Negative Logits
     !...
    -1.21
     myn
    -1.17
     ?...
    -1.16
     NOO
    -1.16
     wien
    -1.15
     inder
    -1.14
     fuf
    -1.12
     maksi
    -1.12
     waer
    -1.09
     keramik
    -1.09
    POSITIVE LOGITS
    <bos>
    1.64
    ...
    0.70
    …
    0.68
    IndentedString
    0.65
    ....
    0.62
     ...
    0.61
     yeah
    0.61
     …
    0.60
    ..
    0.59
     pretty
    0.58
    Activations Density 0.163%

    No Known Activations