© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 6731
    Prev
    Next
    INDEX
    Explanations

    positive expressions related to customer satisfaction

    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
    2034
    +0.17
    0.5%
    1013
    +0.15
    0.4%
    382
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.17
    0.10
    1013
    +0.15
    0.08
    1129
    +0.13
    0.07
    Negative Logits
    Wię
    -0.90
    Gdzie
    -0.75
    Bardzo
    -0.74
     unspeak
    -0.73
     unlaw
    -0.72
    Fitment
    -0.71
    Pozri
    -0.70
    Podob
    -0.70
     Nadie
    -0.70
    Wszyst
    -0.69
    POSITIVE LOGITS
     hina
    0.87
     antik
    0.84
     susun
    0.83
     alkoh
    0.82
     muna
    0.81
     kafe
    0.81
     optik
    0.81
     saha
    0.79
     alip
    0.78
     bayan
    0.78
    Activations Density 0.665%

    No Known Activations