© 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. 16363
    Prev
    Next
    INDEX
    Explanations

    mentions of companies and financial details

    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
    1967
    +0.23
    0.8%
    478
    +0.18
    0.6%
    50
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    478
    +0.23
    0.10
    1533
    +0.18
    0.07
    1967
    +0.15
    0.09
    Negative Logits
     shenan
    -1.10
     intersper
    -0.99
    Noice
    -0.98
    Lmfao
    -0.95
    Cringe
    -0.93
    wieś
    -0.93
    mengg
    -0.93
    Przyp
    -0.92
    Ikr
    -0.91
     unspeak
    -0.90
    POSITIVE LOGITS
     alkoh
    1.47
     torba
    1.41
     silikon
    1.36
     kaos
    1.33
     karton
    1.32
     bunda
    1.26
     kafe
    1.25
     frans
    1.25
     kram
    1.24
     bont
    1.23
    Activations Density 0.602%

    No Known Activations