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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 13458
    Prev
    Next
    INDEX
    Explanations

    references to different types of ships and related terminology

    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
    1757
    +0.12
    0.5%
    492
    +0.11
    0.5%
    1035
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    492
    +0.12
    0.03
    1691
    +0.11
    0.03
    908
    +0.11
    0.02
    Negative Logits
    Madeleine
    -0.49
     Poz
    -0.48
     garante
    -0.45
     تؤ
    -0.45
    Ré
    -0.44
     Br
    -0.44
     BR
    -0.43
     Madeleine
    -0.42
    Demografía
    -0.42
    <?
    -0.42
    POSITIVE LOGITS
     ship
    1.29
     Ship
    1.19
     SHIP
    1.19
    Ship
    1.18
     ships
    1.13
    ship
    1.11
     Ships
    1.11
    ships
    1.02
    SHIP
    1.00
    Ships
    0.98
    Activations Density 0.075%

    No Known Activations