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. 15897
    Prev
    Next
    INDEX
    Explanations

    positive emotional expressions in a community context

    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
    1150
    +0.20
    0.6%
    1013
    +0.17
    0.5%
    1978
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1013
    +0.20
    0.13
    284
    +0.17
    0.12
    2044
    +0.10
    0.13
    Negative Logits
     PLWABN
    -0.55
     récon
    -0.55
     Strukt
    -0.55
     BIBSYS
    -0.55
     cinquième
    -0.54
     confé
    -0.54
     Popis
    -0.51
     Duft
    -0.51
     déplo
    -0.51
    PhysRev
    -0.51
    POSITIVE LOGITS
     Moslem
    0.81
     unspeak
    0.81
     Yugos
    0.72
     Frenchmen
    0.72
     Shakspeare
    0.71
     pamph
    0.70
     cytoplas
    0.70
     unwarran
    0.70
     barbarous
    0.70
     thoughtless
    0.69
    Activations Density 2.013%

    No Known Activations