© 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. 0-RES-JB
    11. 2485
    Prev
    Next
    INDEX
    Explanations

    words related to surrogacy and legal contracts

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1983
    +0.09
    0.3%
    597
    +0.07
    0.2%
    780
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1540
    +0.09
    0.03
    1983
    +0.07
    0.02
    1383
    +0.07
    0.02
    Negative Logits
     Autre
    -1.02
     Leurs
    -0.92
     Leur
    -0.84
     Présentation
    -0.81
     Toujours
    -0.80
     Beaucoup
    -0.80
     Très
    -0.75
     Personne
    -0.74
     Résultat
    -0.74
     Peu
    -0.73
    POSITIVE LOGITS
     Sur
    2.13
     sur
    2.13
    Sur
    1.87
    sur
    1.77
     SUR
    1.46
     fup
    1.30
    SUR
    1.24
     blos
    1.23
     surcharge
    1.21
     vns
    1.18
    Activations Density 0.234%

    No Known Activations