© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 12644
    Prev
    Next
    INDEX
    Explanations

    words related to printed documents or paper forms

    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
    1328
    +0.17
    0.7%
    1096
    +0.15
    0.6%
    331
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1096
    +0.17
    0.02
    1328
    +0.15
    0.02
    554
    +0.15
    0.02
    Negative Logits
     Diener
    -0.65
     fup
    -0.64
     fta
    -0.64
     Bibl
    -0.63
     desir
    -0.61
     fte
    -0.60
     secon
    -0.59
     „,
    -0.58
     Wachs
    -0.58
     Ordre
    -0.58
    POSITIVE LOGITS
     sheet
    1.61
    sheet
    1.45
     sheets
    1.44
     Sheet
    1.43
    Sheet
    1.37
     SHEET
    1.33
    sheets
    1.26
    SHEET
    1.24
     Sheets
    1.20
    heet
    1.17
    Activations Density 0.095%

    No Known Activations