© 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. 4891
    Prev
    Next
    INDEX
    Explanations

    terms related to conducting or running tests and experiments

    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
    555
    +0.14
    0.5%
    411
    +0.13
    0.5%
    1618
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    555
    +0.14
    0.04
    517
    +0.13
    0.03
    411
    +0.13
    0.04
    Negative Logits
     يتيمه
    -0.50
     adal
    -0.50
     kony
    -0.47
     nahilalakip
    -0.47
    harmonie
    -0.46
    irie
    -0.45
    umbra
    -0.44
     bá
    -0.44
    IndentedString
    -0.43
    entum
    -0.43
    POSITIVE LOGITS
     test
    1.12
     Test
    1.11
     tests
    1.07
     Tests
    1.06
     TESTS
    0.98
     TEST
    0.98
    Test
    0.98
    test
    0.97
     testing
    0.97
     Testing
    0.96
    Activations Density 0.087%

    No Known Activations