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. 7938
    Prev
    Next
    INDEX
    Explanations

    terms related to the structure, composition, and health of the human skin, as well as skin conditions like hives and acne

    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
    479
    +0.18
    0.7%
    1328
    +0.16
    0.6%
    866
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.18
    0.03
    866
    +0.16
    0.02
    204
    +0.15
    0.02
    Negative Logits
    IUrlHelper
    -0.54
    UnitTesting
    -0.52
    Mauro
    -0.49
    glMatrixMode
    -0.48
    дивиду
    -0.48
     Mauro
    -0.48
    jsii
    -0.48
     sés
    -0.47
     Treiber
    -0.47
     romero
    -0.47
    POSITIVE LOGITS
     skin
    1.38
    skin
    1.31
    Skin
    1.30
     Skin
    1.29
     SKIN
    1.24
     skins
    1.16
    SKIN
    1.14
     Skins
    1.10
    Skins
    1.06
    skins
    0.99
    Activations Density 0.075%

    No Known Activations