© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4931
    Prev
    Next
    INDEX
    Explanations

    names of people, especially focusing on Hispanic names

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    2011
    +0.12
    0.5%
    492
    +0.11
    0.5%
    1077
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1097
    +0.12
    0.10
    304
    +0.11
    -0.01
    227
    +0.11
    0.08
    Negative Logits
     Mejía
    -2.71
     Darío
    -2.65
     Áng
    -2.59
     Lázaro
    -2.48
     Marín
    -2.39
     Cárdenas
    -2.31
     Valentín
    -2.21
     Domínguez
    -2.12
     Belén
    -2.12
     Mónica
    -2.07
    POSITIVE LOGITS
     wien
    1.62
     aen
    1.59
     „,
    1.57
     fte
    1.57
     ohr
    1.56
     vns
    1.53
     wein
    1.53
     myn
    1.51
     meis
    1.50
     fta
    1.47
    Activations Density 0.798%

    No Known Activations