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. 1302
    Prev
    Next
    INDEX
    Explanations

    terms related to academic concepts and theories, particularly around social production, love, and power

    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
    872
    +0.17
    0.6%
    1533
    +0.13
    0.4%
    1871
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.17
    0.07
    1380
    +0.13
    0.02
    1446
    +0.13
    0.03
    Negative Logits
    Fuer
    -0.59
     لمدة
    -0.57
    citenamefont
    -0.57
    BUYER
    -0.57
    ActionListener
    -0.56
    cshtml
    -0.56
    Newswire
    -0.55
    textbackslash
    -0.54
    }{*}{}
    -0.54
    rawDesc
    -0.53
    POSITIVE LOGITS
     ftu
    1.62
     poff
    1.61
     fta
    1.55
     squa
    1.48
     napoli
    1.47
     thut
    1.46
     perfet
    1.46
     peppa
    1.45
     fign
    1.45
     tranf
    1.45
    Activations Density 0.542%

    No Known Activations