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. 13601
    Prev
    Next
    INDEX
    Explanations

    information related to controversial or debated topics, specifically focusing on legislation and policy decisions regarding drugs

    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
    1499
    +0.11
    0.3%
    1177
    +0.10
    0.3%
    939
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.11
    0.06
    1499
    +0.10
    0.06
    1501
    +0.09
    0.04
    Negative Logits
     nutella
    -0.70
     Quinoa
    -0.67
    Cześć
    -0.64
    Noice
    -0.63
    pentru
    -0.63
     volon
    -0.62
     amigurumi
    -0.60
    Hahah
    -0.59
    Xoxo
    -0.59
    Lmfao
    -0.58
    POSITIVE LOGITS
     ekos
    0.86
     panik
    0.84
     praktik
    0.82
     prakti
    0.80
     kafe
    0.80
     optik
    0.78
     kosme
    0.78
     kriminal
    0.78
     silikon
    0.77
     protokol
    0.76
    Activations Density 0.483%

    No Known Activations