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. 218
    Prev
    Next
    INDEX
    Explanations

    phrases related to small businesses and their interactions with the economy and policy-making

    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
    1445
    +0.09
    0.3%
    198
    +0.09
    0.3%
    1403
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    198
    +0.09
    0.04
    274
    +0.09
    0.03
    1416
    +0.09
    0.03
    Negative Logits
     increa
    -1.41
     intersper
    -1.36
     guarante
    -1.36
     maneu
    -1.36
     volunte
    -1.35
     encomp
    -1.34
     disagre
    -1.32
     perfet
    -1.31
     affor
    -1.30
     indestru
    -1.29
    POSITIVE LOGITS
     businesses
    1.09
     business
    0.90
     Businesses
    0.87
    Businesses
    0.81
     Business
    0.80
    businesses
    0.78
    business
    0.77
    Business
    0.75
    InputBorder
    0.72
     enterprises
    0.71
    Activations Density 0.360%

    No Known Activations