© 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. 16105
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical lifting or raising objects

    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
    489
    +0.13
    0.5%
    61
    +0.12
    0.5%
    1565
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1565
    +0.13
    0.02
    1805
    +0.12
    0.02
    489
    +0.12
    0.02
    Negative Logits
     bosch
    -0.64
     unlaw
    -0.63
     Stretcher
    -0.60
     Thermometer
    -0.58
     pylab
    -0.58
     unden
    -0.57
     cabrio
    -0.56
     michelin
    -0.56
     milano
    -0.56
     oleo
    -0.56
    POSITIVE LOGITS
     lift
    1.37
     lifted
    1.29
     lifting
    1.26
     lifts
    1.23
    lift
    1.20
     Lift
    1.16
    Lift
    1.11
    Lifting
    1.05
     LIFT
    0.99
    lifted
    0.99
    Activations Density 0.072%

    No Known Activations