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. 557
    Prev
    Next
    INDEX
    Explanations

    the word "but" in sentences where the speaker expresses contrasting or conflicting views

    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
    605
    +0.14
    0.5%
    1445
    +0.13
    0.4%
    555
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1276
    +0.14
    0.07
    1677
    +0.13
    0.07
    555
    +0.13
    0.05
    Negative Logits
     lele
    -1.24
     robus
    -1.20
     jep
    -1.14
     dises
    -1.08
     hina
    -1.07
     keramik
    -1.06
     sappi
    -1.04
     antik
    -1.04
     teras
    -1.04
     gend
    -1.03
    POSITIVE LOGITS
     it
    0.84
     there
    0.79
     they
    0.77
     if
    0.73
     we
    0.69
     I
    0.69
     hey
    0.67
     you
    0.65
     nobody
    0.64
     but
    0.64
    Activations Density 0.167%

    No Known Activations