© 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. 10545
    Prev
    Next
    INDEX
    Explanations

    instances where the speaker goes off on tangents

    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
    872
    +0.10
    0.3%
    2015
    +0.09
    0.2%
    906
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1478
    +0.10
    0.04
    2005
    +0.09
    0.03
    598
    +0.08
    0.03
    Negative Logits
    Xoxo
    -0.70
     rafra
    -0.67
     palio
    -0.65
     Diction
    -0.65
     Simult
    -0.64
    Warmly
    -0.64
     FFFF
    -0.64
     Cfr
    -0.64
     riviera
    -0.63
     sappi
    -0.62
    POSITIVE LOGITS
     digress
    1.11
     back
    0.71
     rambling
    0.62
    Datuak
    0.59
    findpost
    0.59
    back
    0.58
    Back
    0.58
     topic
    0.58
     BACK
    0.56
     Back
    0.56
    Activations Density 0.339%

    No Known Activations