© 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. 15202
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events or processes

    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
    370
    +0.11
    0.3%
    1778
    +0.09
    0.3%
    1145
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    370
    +0.11
    0.02
    474
    +0.09
    0.02
    1604
    +0.09
    0.02
    Negative Logits
     utop
    -0.68
     kram
    -0.64
     solidar
    -0.63
     bombe
    -0.62
     ideolog
    -0.61
     vola
    -0.60
     aquare
    -0.59
     Bibl
    -0.58
     lomb
    -0.58
     perle
    -0.57
    POSITIVE LOGITS
     followed
    1.06
     Followed
    0.98
    followed
    0.97
    Followed
    0.85
     seguido
    0.77
    folgt
    0.69
     gevol
    0.68
     diikuti
    0.66
     follow
    0.62
     FOLLOW
    0.62
    Activations Density 0.104%

    No Known Activations