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. 478
    Prev
    Next
    INDEX
    Explanations

    years and dates mentioned in a plot

    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
    1343
    +0.13
    0.4%
    776
    +0.10
    0.3%
    198
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1614
    +0.13
    0.05
    573
    +0.10
    0.04
    535
    +0.08
    0.04
    Negative Logits
     Shakspeare
    -1.17
     impractica
    -1.09
     anhyd
    -0.99
     tolerably
    -0.97
     unlaw
    -0.96
     Grecian
    -0.95
     Mahomet
    -0.94
     liberality
    -0.94
     Daven
    -0.93
     felicity
    -0.90
    POSITIVE LOGITS
     Jerusal
    1.01
     Wikiquote
    0.99
     spion
    0.97
     alkoh
    0.94
     robus
    0.90
     manuten
    0.88
     uhr
    0.88
     marte
    0.88
     utop
    0.88
     biograf
    0.86
    Activations Density 0.125%

    No Known Activations