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. 1381
    Prev
    Next
    INDEX
    Explanations

    timestamps in a specific format

    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
    +0.19
    0.6%
    612
    +0.15
    0.5%
    814
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.19
    0.06
    612
    +0.15
    0.01
    1036
    +0.13
    0.01
    Negative Logits
     betweenstory
    -0.52
     unworthy
    -0.51
     gyhoeddwyd
    -0.48
     gratify
    -0.46
     shrill
    -0.45
     pharynx
    -0.45
     quivering
    -0.45
     TBI
    -0.44
    cnpj
    -0.44
    ztő
    -0.43
    POSITIVE LOGITS
     aen
    0.93
     alkoh
    0.92
     inder
    0.88
     meis
    0.87
     sii
    0.85
     kosme
    0.84
     handels
    0.82
     ciment
    0.82
     franz
    0.81
     gmbh
    0.81
    Activations Density 0.292%

    No Known Activations