© 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. 5215
    Prev
    Next
    INDEX
    Explanations

    specific adjectives or phrases indicating a positive description

    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
    674
    +0.42
    1.5%
    1177
    +0.14
    0.5%
    1842
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.42
    0.01
    569
    +0.14
    0.04
    944
    +0.11
    0.01
    Negative Logits
    setH
    -0.59
     My
    -0.53
    newVal
    -0.53
     B
    -0.53
     By
    -0.51
     H
    -0.51
     F
    -0.51
     P
    -0.51
     Some
    -0.50
     More
    -0.50
    POSITIVE LOGITS
     sappi
    1.17
     incess
    1.09
     ordina
    1.04
     !...
    1.04
     vogli
    1.01
     chande
    1.00
     vorrei
    0.99
     batte
    0.99
     poichè
    0.99
     dises
    0.98
    Activations Density 0.535%

    No Known Activations