© 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. 14927
    Prev
    Next
    INDEX
    Explanations

    URLs

    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
    1535
    +0.10
    0.3%
    553
    +0.09
    0.3%
    1926
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    553
    +0.10
    0.02
    449
    +0.09
    0.01
    210
    +0.08
    0.02
    Negative Logits
     real
    -0.56
     say
    -0.52
     carrying
    -0.52
    时
    -0.51
     خبرگزاری
    -0.51
     under
    -0.51
    фии
    -0.51
     ناز
    -0.50
     ten
    -0.50
     record
    -0.49
    POSITIVE LOGITS
     sappi
    1.28
     erad
    1.23
     accla
    1.19
     conspic
    1.18
     inev
    1.15
     embra
    1.14
     impractica
    1.12
     reluct
    1.11
     purcha
    1.11
     michelin
    1.09
    Activations Density 0.021%

    No Known Activations