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. 1693
    Prev
    Next
    INDEX
    Explanations

    expressions of disbelief or surprise

    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
    1265
    +0.11
    0.4%
    1741
    +0.10
    0.3%
    381
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.11
    0.02
    689
    +0.10
    0.02
    521
    +0.10
    0.02
    Negative Logits
    Hahahahaha
    -0.68
    Hahahaha
    -0.66
    ulipas
    -0.61
    viedo
    -0.61
     meras
    -0.60
    ഊ
    -0.60
     €/
    -0.59
     girasol
    -0.55
     naran
    -0.55
    })->
    -0.55
    POSITIVE LOGITS
     Oh
    0.91
     oh
    0.86
    Oh
    0.84
     prouve
    0.81
     ferait
    0.77
     scrat
    0.74
     OH
    0.72
     pooh
    0.69
     défend
    0.67
     reconno
    0.67
    Activations Density 0.032%

    No Known Activations