© 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. 6349
    Prev
    Next
    INDEX
    Explanations

    verbs related to actions of departure or abandonment

    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
    172
    +0.14
    0.5%
    1096
    +0.14
    0.4%
    481
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.14
    0.04
    1096
    +0.14
    0.04
    481
    +0.12
    0.04
    Negative Logits
     raste
    -0.57
     vna
    -0.52
     Forse
    -0.52
     Sigue
    -0.52
     Mentre
    -0.49
    logFile
    -0.49
     Infatti
    -0.48
     Inoltre
    -0.48
    Warmly
    -0.47
     Pelo
    -0.47
    POSITIVE LOGITS
     leave
    1.15
     LEAVE
    1.12
     Leave
    1.07
    leave
    1.05
     leaves
    1.05
    Leave
    1.02
    leaves
    1.00
     leaving
    0.98
     Leaves
    0.92
     Leaving
    0.90
    Activations Density 0.064%

    No Known Activations