© 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. 12063
    Prev
    Next
    INDEX
    Explanations

    words related to dirtiness, negative actions, and controversy

    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
    1035
    +0.12
    0.4%
    168
    +0.11
    0.4%
    1325
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.12
    0.03
    147
    +0.11
    0.01
    1035
    +0.10
    0.03
    Negative Logits
     affor
    -0.66
     unlaw
    -0.58
     berea
    -0.55
     guarante
    -0.55
     Gypsum
    -0.55
     shenan
    -0.53
     attemp
    -0.53
     fortn
    -0.53
     Uptake
    -0.53
     suscep
    -0.53
    POSITIVE LOGITS
     dirty
    1.14
    dirty
    1.10
     dirt
    1.01
     Dirty
    1.00
    Dirty
    0.97
    dirt
    0.84
     contamination
    0.82
     Dirt
    0.80
    contamination
    0.79
    Dirt
    0.76
    Activations Density 0.115%

    No Known Activations