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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16139
    Prev
    Next
    INDEX
    Explanations

    information related to financial aspects, such as net worth and monetary figures

    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
    1343
    +0.19
    0.7%
    612
    +0.16
    0.5%
    1150
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    612
    +0.19
    0.00
    227
    +0.16
    0.07
    1343
    +0.15
    0.07
    Negative Logits
     perfon
    -1.02
     ftu
    -1.01
     fta
    -1.00
     fto
    -0.99
     greate
    -0.98
     tranf
    -0.98
     fuf
    -0.97
     embra
    -0.95
     superintend
    -0.94
     guarante
    -0.93
    POSITIVE LOGITS
     gradova
    0.58
    ReusableCell
    0.52
    StandardCharsets
    0.49
    TextWatcher
    0.47
    ,:),
    0.46
    ,:)
    0.45
    yticks
    0.43
    setCellStyle
    0.42
     naran
    0.42
     للمعارف
    0.42
    Activations Density 0.665%

    No Known Activations