© 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. 2522
    Prev
    Next
    INDEX
    Explanations

    references to a specific geographical location named Hudson

    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
    990
    +0.12
    0.4%
    1334
    +0.10
    0.3%
    920
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.12
    0.03
    990
    +0.10
    0.03
    690
    +0.09
    0.03
    Negative Logits
     че
    -0.60
     pay
    -0.59
    ്ല
    -0.58
    вя
    -0.58
     er
    -0.56
    張
    -0.55
     נע
    -0.55
    张
    -0.55
    공
    -0.55
     across
    -0.54
    POSITIVE LOGITS
     Hudson
    2.82
    Hudson
    2.56
     hudson
    2.22
     inev
    1.48
     emphat
    1.47
     reluct
    1.46
     suscep
    1.45
     embra
    1.44
     maneu
    1.44
     accla
    1.44
    Activations Density 0.225%

    No Known Activations