© 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. 0-RES-JB
    11. 1124
    Prev
    Next
    INDEX
    Explanations

    phrases related to strong criticism or condemnation

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1937
    +0.13
    0.4%
    889
    +0.12
    0.4%
    131
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.13
    0.03
    1130
    +0.12
    0.02
    387
    +0.09
    0.02
    Negative Logits
    <bos>
    -0.90
     endow
    -0.74
     gratify
    -0.67
     intersper
    -0.66
     exaggerate
    -0.66
     vainly
    -0.65
     harmonize
    -0.64
     subdue
    -0.64
     banish
    -0.64
     liberate
    -0.64
    POSITIVE LOGITS
     dam
    2.78
     Dam
    2.68
    Dam
    2.57
    dam
    2.35
     dams
    2.15
     Dams
    2.05
     DAM
    2.01
    DAM
    1.73
    dams
    1.57
     Damas
    1.25
    Activations Density 0.167%

    No Known Activations