© 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. 13725
    Prev
    Next
    INDEX
    Explanations

    references to different types of bottles and containers

    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
    +0.17
    0.7%
    1926
    +0.16
    0.6%
    1573
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1926
    +0.17
    0.02
    1573
    +0.16
    0.02
    889
    +0.14
    0.02
    Negative Logits
     Himmels
    -0.62
    vanni
    -0.58
     calvin
    -0.58
    ceas
    -0.57
     triump
    -0.56
     كومونز
    -0.56
     dante
    -0.55
     Leip
    -0.55
     fap
    -0.55
    ConstraintMaker
    -0.55
    POSITIVE LOGITS
     bottle
    1.47
     bottles
    1.39
     Bottle
    1.30
    bottle
    1.28
    Bottle
    1.25
    Bott
    1.20
     Bott
    1.19
     Bottles
    1.16
     BOTT
    1.12
     bottled
    1.08
    Activations Density 0.088%

    No Known Activations