© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 313
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific individual named Healy

    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
    1548
    +0.08
    0.2%
    1065
    +0.08
    0.2%
    257
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.08
    0.04
    1343
    +0.08
    0.07
    1120
    +0.07
    0.07
    Negative Logits
    cabul
    -0.54
    intendent
    -0.52
     er
    -0.50
     im
    -0.49
     vom
    -0.49
    mability
    -0.49
    journ
    -0.49
    -
    -0.48
    ashier
    -0.48
     פון
    -0.48
    POSITIVE LOGITS
    aly
    1.29
     volunte
    1.21
     guarante
    1.11
     thut
    1.10
     disagre
    1.08
     inev
    1.07
     quitted
    1.06
     coö
    1.06
     kte
    1.06
     accla
    1.05
    Activations Density 0.499%

    No Known Activations