© 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. 4699
    Prev
    Next
    INDEX
    Explanations

    names, particularly of people

    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
    32
    +0.18
    0.8%
    411
    +0.15
    0.6%
    976
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    976
    +0.18
    0.03
    1145
    +0.15
    0.03
    896
    +0.14
    0.02
    Negative Logits
     prouve
    -0.61
    sightly
    -0.59
    ruly
    -0.57
     émer
    -0.57
    Dermott
    -0.56
    relenting
    -0.56
     Glou
    -0.55
    Cormack
    -0.55
     Kild
    -0.55
     levier
    -0.54
    POSITIVE LOGITS
     blank
    1.20
     Blank
    1.19
    blank
    1.18
     Blan
    1.17
    Blan
    1.15
     blan
    1.13
    Blank
    1.12
    blan
    1.09
     BLANK
    1.09
     blanks
    1.03
    Activations Density 0.146%

    No Known Activations