© 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. 12288
    Prev
    Next
    INDEX
    Explanations

    legal terms and permissions related phrases

    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
    1150
    +0.23
    0.8%
    1438
    +0.14
    0.5%
    674
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1150
    +0.23
    0.05
    284
    +0.14
    0.08
    332
    +0.14
    0.05
    Negative Logits
     nece
    -1.46
     surfact
    -1.40
     unlaw
    -1.38
     ?...
    -1.37
     effe
    -1.32
     NOO
    -1.31
     desir
    -1.31
     swarovski
    -1.28
     emphat
    -1.27
     sappi
    -1.25
    POSITIVE LOGITS
    <eos>
    1.15
    .
    1.11
    。
    0.95
    .”
    0.89
    ↵↵
    0.89
    .\\
    0.88
    !
    0.84
    ."
    0.83
    ↵↵↵
    0.83
    .)
    0.81
    Activations Density 0.595%

    No Known Activations