Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 649
    Prev
    Next
    INDEX
    Explanations

    medical terms and health-related information

    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
    946
    +0.10
    0.3%
    1553
    +0.10
    0.3%
    738
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1114
    +0.10
    0.04
    946
    +0.10
    0.05
    1553
    +0.09
    0.05
    Negative Logits
     franz
    -1.07
     wien
    -1.07
     oner
    -1.07
     nutr
    -1.05
     mef
    -1.05
     daf
    -1.05
     erec
    -1.05
     doman
    -1.04
     effe
    -1.04
     „,
    -1.03
    POSITIVE LOGITS
    <bos>
    0.96
     consultation
    0.73
     appointment
    0.72
     appointments
    0.69
     diagnosis
    0.66
     consult
    0.65
     treatment
    0.65
     consultations
    0.65
     services
    0.63
     diagnosed
    0.60
    Activations Density 0.393%

    No Known Activations