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-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3006
    Prev
    Next
    INDEX
    Explanations

    mentions of the media outlet "Breitbart"

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1573
    +0.15
    0.5%
    1387
    +0.14
    0.5%
    528
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1573
    +0.15
    0.02
    1387
    +0.14
    0.02
    528
    +0.13
    0.02
    Negative Logits
    setVerticalGroup
    -0.48
    GINIA
    -0.46
    YMS
    -0.45
    PerformLayout
    -0.45
    ی
    -0.44
     Ленин
    -0.44
    hood
    -0.44
    contentLoaded
    -0.44
     Ontario
    -0.44
    ("/:
    -0.43
    POSITIVE LOGITS
     Breit
    1.45
     eyel
    0.92
     Traité
    0.92
     depic
    0.90
     milf
    0.90
     hairc
    0.90
     squa
    0.88
     casio
    0.88
     applau
    0.88
     AMAZ
    0.87
    Activations Density 0.115%

    No Known Activations