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. 233
    Prev
    Next
    INDEX
    Explanations

    adverbs of degree, particularly focusing on the intensity or extremeness of a situation

    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
    994
    +0.12
    0.4%
    674
    +0.09
    0.3%
    1262
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.12
    0.03
    755
    +0.09
    0.03
    994
    +0.08
    0.03
    Negative Logits
     ert
    -0.63
     bera
    -0.56
     kand
    -0.56
     gend
    -0.53
     ria
    -0.52
     ete
    -0.51
     krist
    -0.51
     tornare
    -0.51
     praktik
    -0.50
     kosme
    -0.50
    POSITIVE LOGITS
     liberality
    0.82
     unlaw
    0.80
     unwarran
    0.80
     cushi
    0.79
     hairc
    0.76
     Février
    0.76
     constaté
    0.75
     Décembre
    0.75
     pamph
    0.74
     oamen
    0.74
    Activations Density 0.081%

    No Known Activations