© 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. 360
    Prev
    Next
    INDEX
    Explanations

    details and instructions related to roasting various foods

    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
    421
    +0.10
    0.3%
    1387
    +0.09
    0.3%
    544
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1120
    +0.10
    0.04
    1639
    +0.09
    0.03
    690
    +0.08
    0.04
    Negative Logits
     induced
    -0.73
     induce
    -0.70
    induced
    -0.64
     induces
    -0.59
    onViewCreated
    -0.56
    }{|
    -0.53
    indu
    -0.53
    DidLoad
    -0.52
     lead
    -0.52
    }{||
    -0.52
    POSITIVE LOGITS
     liberality
    1.27
     Roast
    1.25
     unwarran
    1.20
     Roasted
    1.19
     roast
    1.17
     unlaw
    1.15
    Roast
    1.14
    Roasted
    1.14
     roasting
    1.12
     volunte
    1.11
    Activations Density 0.333%

    No Known Activations