© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 4523
    Prev
    Next
    INDEX
    Explanations

    words related to reviewing or critiquing

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1013
    +0.12
    0.3%
    1438
    +0.11
    0.3%
    1081
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.12
    0.07
    2044
    +0.11
    0.07
    1013
    +0.09
    0.07
    Negative Logits
     ?...
    -1.50
     effe
    -1.43
     emphat
    -1.43
     !...
    -1.41
     fuf
    -1.39
     fep
    -1.35
     fta
    -1.34
     increa
    -1.34
     fte
    -1.34
     „,
    -1.31
    POSITIVE LOGITS
    .
    0.87
     due
    0.79
     because
    0.78
    。
    0.68
    because
    0.67
    <bos>
    0.67
     since
    0.65
     thanks
    0.65
    !
    0.64
     nonetheless
    0.63
    Activations Density 0.650%

    No Known Activations