© 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. 7133
    Prev
    Next
    INDEX
    Explanations

    references to working or labor-related activities

    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
    1339
    +0.11
    0.4%
    1385
    +0.11
    0.4%
    25
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1805
    +0.11
    0.05
    1865
    +0.11
    0.04
    25
    +0.10
    0.05
    Negative Logits
    Εκ
    -0.63
    Ảnh
    -0.57
    CompleteListener
    -0.57
    QUADS
    -0.56
    ഊ
    -0.56
    SystemColors
    -0.55
    SuccessListener
    -0.54
    XmlRootElement
    -0.53
    InkWell
    -0.53
    putBoolean
    -0.52
    POSITIVE LOGITS
     Augu
    1.25
     purcha
    1.17
     ?...
    1.16
     fta
    1.14
     !...
    1.13
     alre
    1.11
     increa
    1.09
     fto
    1.09
     effe
    1.09
     wherea
    1.09
    Activations Density 0.324%

    No Known Activations