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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4835
    Prev
    Next
    INDEX
    Explanations

    mentions of human body parts, particularly arms

    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
    +0.17
    0.7%
    1872
    +0.13
    0.5%
    1413
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    479
    +0.17
    0.04
    1872
    +0.13
    0.03
    1639
    +0.12
    0.02
    Negative Logits
     zanah
    -0.46
     Gregorio
    -0.45
    HostException
    -0.44
    FlatAppearance
    -0.44
     Donato
    -0.44
     Breathable
    -0.43
    ıyoruz
    -0.43
     linkovi
    -0.43
    Demografía
    -0.43
    Bele
    -0.41
    POSITIVE LOGITS
     arm
    1.34
     Arm
    1.34
     arms
    1.30
    Arm
    1.29
     ARM
    1.23
    Arms
    1.21
    arm
    1.21
     Arms
    1.21
    ARM
    1.16
    arms
    1.16
    Activations Density 0.055%

    No Known Activations