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. 8447
    Prev
    Next
    INDEX
    Explanations

    opinions expressed in newspaper editorials

    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
    1895
    +0.18
    0.8%
    597
    +0.16
    0.7%
    871
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1895
    +0.18
    0.03
    597
    +0.16
    0.02
    1778
    +0.15
    0.02
    Negative Logits
    oblotting
    -0.56
     autorytatywna
    -0.54
    Nascimento
    -0.53
    GraphicsUnit
    -0.50
    lasia
    -0.47
    Sklici
    -0.46
    CELLANEOUS
    -0.46
     geweest
    -0.46
    bacillus
    -0.46
    marshaller
    -0.46
    POSITIVE LOGITS
     Op
    1.22
     optik
    1.16
     op
    1.15
    Op
    1.10
     encomp
    1.08
     OP
    1.07
     pessi
    1.04
     ops
    1.03
    op
    1.03
     Ops
    1.01
    Activations Density 0.093%

    No Known Activations