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. 15822
    Prev
    Next
    INDEX
    Explanations

    information related to transportation systems and sports leagues

    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
    1967
    +0.17
    0.5%
    1978
    +0.16
    0.5%
    752
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1904
    +0.17
    0.06
    1967
    +0.16
    0.05
    297
    +0.12
    0.05
    Negative Logits
     at
    -0.72
     a
    -0.72
     no
    -0.72
     in
    -0.71
     for
    -0.70
     or
    -0.69
     as
    -0.69
     on
    -0.69
     son
    -0.68
     with
    -0.68
    POSITIVE LOGITS
     alkoh
    2.11
     silikon
    2.00
     kosme
    1.96
     makro
    1.94
     kön
    1.93
     antik
    1.88
     keramik
    1.86
     karton
    1.84
     kafe
    1.84
     allarg
    1.83
    Activations Density 0.221%

    No Known Activations