© 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 EvalsExportsAPI 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. 13198
    Prev
    Next
    INDEX
    Explanations

    medical-related terms such as therapy, rehabilitation, and therapist

    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
    1034
    +0.21
    0.8%
    1896
    +0.16
    0.6%
    251
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1034
    +0.21
    0.03
    1896
    +0.16
    0.02
    1276
    +0.14
    0.02
    Negative Logits
     matur
    -0.57
     تضيفلها
    -0.56
     impon
    -0.54
     Himo
    -0.53
     uncin
    -0.51
    scut
    -0.50
     obligator
    -0.49
     BnF
    -0.49
     nutr
    -0.49
     impe
    -0.49
    POSITIVE LOGITS
     therapy
    1.30
     Therapy
    1.23
    Therapy
    1.16
     therapist
    1.06
    therapy
    1.05
     therapists
    1.04
     Therapist
    1.02
     therapies
    1.01
     THERAPY
    1.01
     Therap
    0.96
    Activations Density 0.090%

    No Known Activations