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. 15419
    Prev
    Next
    INDEX
    Explanations

    dates, percentages, names, and numbers

    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
    1577
    +0.42
    1.6%
    964
    +0.21
    0.8%
    1343
    +0.18
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    184
    +0.42
    0.06
    1577
    +0.21
    0.14
    1343
    +0.18
    0.12
    Negative Logits
     reluct
    -1.42
     accla
    -1.38
     emphat
    -1.32
     disagre
    -1.30
     affor
    -1.27
     shenan
    -1.26
     maneu
    -1.26
     increa
    -1.25
     philanth
    -1.24
     pamph
    -1.19
    POSITIVE LOGITS
    parsedMessage
    0.62
     للمعارف
    0.56
    ValueStyle
    0.53
    Попис
    0.51
    wikidata
    0.50
    ANTLR
    0.48
    ieR
    0.48
    enumi
    0.47
     pinulongan
    0.47
    CodedInputStream
    0.46
    Activations Density 2.251%

    No Known Activations