© 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. 10542
    Prev
    Next
    INDEX
    Explanations

    information about online courses and education

    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
    1013
    +0.13
    0.4%
    1403
    +0.12
    0.4%
    678
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1336
    +0.13
    0.05
    1823
    +0.12
    0.03
    841
    +0.11
    0.02
    Negative Logits
     lavorato
    -0.76
     appunt
    -0.67
     provato
    -0.64
     împre
    -0.63
     sentito
    -0.62
     soste
    -0.60
     jouant
    -0.60
     automne
    -0.60
     ricevuto
    -0.60
     îna
    -0.59
    POSITIVE LOGITS
     courses
    0.81
     Pamph
    0.76
     shenan
    0.76
     workshops
    0.76
     sessions
    0.74
     Courses
    0.74
     Taught
    0.74
     impractica
    0.72
     fortn
    0.70
     programs
    0.70
    Activations Density 0.490%

    No Known Activations