© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3670
    Prev
    Next
    INDEX
    Explanations

    information pertaining to dietary habits and their effects, specifically focusing on sources of nutrients and their impact on health, including fatty acids, hormones, and inflammatory responses

    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
    184
    +0.13
    0.4%
    1842
    +0.12
    0.3%
    1819
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1842
    +0.13
    0.05
    184
    +0.12
    0.02
    284
    +0.09
    0.05
    Negative Logits
     sappi
    -1.21
     affez
    -1.16
     doman
    -1.15
     batte
    -1.15
     socie
    -1.13
     compen
    -1.13
     ivi
    -1.11
     ridu
    -1.11
     nutr
    -1.10
     peculi
    -1.10
    POSITIVE LOGITS
     which
    1.46
    which
    1.33
    Which
    1.16
     Which
    1.14
     WHICH
    1.00
     whose
    0.95
    ซึ่ง
    0.90
    hich
    0.85
     that
    0.80
     ซึ่ง
    0.78
    Activations Density 0.398%

    No Known Activations