Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 1266
    Prev
    Next
    INDEX
    Explanations

    mentions of corruption and unethical behavior, especially in public and political contexts

    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
    889
    +0.14
    0.5%
    1233
    +0.11
    0.4%
    1026
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    889
    +0.14
    0.02
    1233
    +0.11
    0.02
    976
    +0.10
    0.02
    Negative Logits
     volunte
    -0.98
     guarante
    -0.94
     affor
    -0.92
     impra
    -0.92
     increa
    -0.91
     fortn
    -0.90
     effe
    -0.89
     reluct
    -0.87
     tanga
    -0.86
     sovere
    -0.86
    POSITIVE LOGITS
     corruption
    1.22
    corruption
    1.12
     corrupt
    1.06
     Corruption
    1.04
    Corruption
    1.04
     corrupted
    0.83
     Cor
    0.82
    Cor
    0.73
     COR
    0.72
     corrup
    0.70
    Activations Density 0.060%

    No Known Activations