© 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. 11719
    Prev
    Next
    INDEX
    Explanations

    phrases related to direct connections or interactions between entities

    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
    316
    +0.16
    0.5%
    1622
    +0.14
    0.5%
    1981
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.16
    0.05
    1622
    +0.14
    0.03
    1981
    +0.12
    0.03
    Negative Logits
     maneu
    -0.83
     encomp
    -0.82
     accla
    -0.78
     fuf
    -0.77
     inev
    -0.77
     increa
    -0.75
     ineffec
    -0.74
     Pamph
    -0.74
     attemp
    -0.73
     reluct
    -0.73
    POSITIVE LOGITS
    Direct
    1.08
    direct
    1.06
     direct
    1.01
     directly
    1.01
     Direct
    0.99
    directly
    0.92
     DIRECT
    0.92
    DIRECT
    0.90
    IRECT
    0.83
     Directly
    0.79
    Activations Density 0.095%

    No Known Activations