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. 710
    Prev
    Next
    INDEX
    Explanations

    references to folk culture and its related concepts

    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
    437
    +0.14
    0.7%
    331
    +0.13
    0.6%
    1482
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    437
    +0.14
    0.02
    227
    +0.13
    0.02
    1892
    +0.12
    0.01
    Negative Logits
    <bos>
    -1.26
    djangoproject
    -0.75
    XmlAccessType
    -0.72
    uxxxx
    -0.71
    awtextra
    -0.70
    DotNetBar
    -0.70
    resizingMask
    -0.69
    Personendaten
    -0.68
    contentLoaded
    -0.68
    PostInfinity
    -0.68
    POSITIVE LOGITS
     Folk
    1.41
     cæ
    1.31
     Juf
    1.30
    Folk
    1.30
     quæ
    1.29
     folk
    1.29
     habet
    1.23
     eorum
    1.21
     unlaw
    1.18
     Cuen
    1.17
    Activations Density 0.132%

    No Known Activations