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. 259
    Prev
    Next
    INDEX
    Explanations

    words related to decisions, discussions, and explanations

    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
    2034
    +0.10
    0.3%
    1150
    +0.09
    0.3%
    1735
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.06
    1079
    +0.09
    0.03
    332
    +0.09
    0.04
    Negative Logits
     increa
    -1.86
     unden
    -1.80
     depic
    -1.78
     affor
    -1.74
     inev
    -1.70
     fuf
    -1.67
     secon
    -1.66
     desir
    -1.66
     encomp
    -1.63
     guarante
    -1.62
    POSITIVE LOGITS
    InteropServices
    0.73
    getItemId
    0.68
    ."/
    0.67
    flexGrow
    0.67
    JCheckBox
    0.66
    .
    0.65
    marginVertical
    0.65
    paddingVertical
    0.64
    ContentAsync
    0.63
    Seeder
    0.63
    Activations Density 0.326%

    No Known Activations