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. 320
    Prev
    Next
    INDEX
    Explanations

    topics related to legal and social justice issues, particularly focusing on immigration, human trafficking, racial discrimination, and legal doctrines like "separate but equal."

    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
    1978
    +0.16
    0.5%
    468
    +0.15
    0.5%
    394
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1261
    +0.16
    0.01
    468
    +0.15
    0.03
    1597
    +0.11
    0.02
    Negative Logits
     lamborghini
    -0.92
     lidl
    -0.91
     tucson
    -0.88
     tsl
    -0.87
     milf
    -0.87
     toshiba
    -0.85
     toledo
    -0.84
     panasonic
    -0.82
     stockholm
    -0.81
     eiffel
    -0.81
    POSITIVE LOGITS
    ”
    0.81
    "
    0.78
    ":
    0.76
    </em>
    0.74
    ",
    0.72
    ”,
    0.72
    "?
    0.72
    </i>
    0.70
    </u>
    0.70
    ”?
    0.69
    Activations Density 0.184%

    No Known Activations