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. 8442
    Prev
    Next
    INDEX
    Explanations

    references to government policies and reports

    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
    1741
    +0.28
    1.0%
    50
    +0.23
    0.8%
    227
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    16
    +0.28
    0.09
    50
    +0.23
    0.06
    1967
    +0.17
    0.06
    Negative Logits
     lmfao
    -0.81
     anteriorly
    -0.71
     purée
    -0.71
     overcrow
    -0.69
     teljesen
    -0.67
     erős
    -0.67
     herido
    -0.65
     všem
    -0.64
     subgoals
    -0.63
     inkább
    -0.63
    POSITIVE LOGITS
     Chá
    1.15
     Nö
    1.12
     préc
    1.02
     Jä
    1.02
     Bâ
    1.01
     gouver
    1.00
     Mâ
    0.99
     Præ
    0.99
     pié
    0.98
     Câ
    0.98
    Activations Density 0.391%

    No Known Activations