© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14295
    Prev
    Next
    INDEX
    Explanations

    terms related to maritime activities, such as ships, sea, and naval battles

    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
    939
    +0.12
    0.3%
    1120
    +0.10
    0.3%
    908
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.12
    0.06
    1038
    +0.10
    0.04
    946
    +0.10
    0.05
    Negative Logits
     krab
    -0.91
     kado
    -0.85
     hek
    -0.80
     moza
    -0.79
     lapto
    -0.78
     vola
    -0.77
     kram
    -0.75
     handels
    -0.73
     bombe
    -0.73
     psychiat
    -0.73
    POSITIVE LOGITS
     hentai
    0.85
     hasbro
    0.85
     ecru
    0.84
     McLaugh
    0.81
     woollen
    0.77
    Fuckin
    0.77
     nutella
    0.75
     simpsons
    0.74
     chibi
    0.74
     pyp
    0.73
    Activations Density 0.571%

    No Known Activations