Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 6769
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or critiques

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.24
    1.0%
    1343
    +0.16
    0.7%
    1967
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.24
    0.02
    609
    +0.16
    0.01
    924
    +0.11
    0.01
    Negative Logits
    <bos>
    -2.62
    ⓧ
    -0.70
     springfox
    -0.69
    ArrowToggle
    -0.67
    //};
    -0.66
    ///**
    -0.66
    //});
    -0.65
    HasAnnotation
    -0.64
     SEDS
    -0.64
    LookAnd
    -0.64
    POSITIVE LOGITS
     affor
    1.01
     stockholm
    0.97
     frankfurt
    0.96
     maneu
    0.96
     carrefour
    0.94
     eiffel
    0.94
     barcelona
    0.93
     volunte
    0.87
     practition
    0.85
     emphat
    0.85
    Activations Density 0.016%

    No Known Activations