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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1807
    Prev
    Next
    INDEX
    Explanations

    phrases indicating regret or reflection on past actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.13
    0.5%
    1013
    +0.10
    0.4%
    1437
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    908
    +0.13
    0.03
    1372
    +0.10
    0.04
    626
    +0.10
    0.04
    Negative Logits
    <bos>
    -2.33
     are
    -0.76
     is
    -0.73
     now
    -0.69
     currently
    -0.68
     e
    -0.68
     r
    -0.67
     will
    -0.67
     often
    -0.66
    echo
    -0.66
    POSITIVE LOGITS
     Minang
    1.59
     bandung
    1.50
     Juf
    1.48
     ecru
    1.48
     swarovski
    1.47
     bordeaux
    1.45
     eiffel
    1.44
     maroc
    1.41
     magis
    1.40
     impra
    1.40
    Activations Density 0.305%

    No Known Activations