© 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. 15214
    Prev
    Next
    INDEX
    Explanations

    financial and business-related terms

    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
    1553
    +0.10
    0.3%
    1445
    +0.10
    0.3%
    1385
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1683
    +0.10
    0.04
    1553
    +0.10
    0.04
    934
    +0.08
    0.02
    Negative Logits
     desir
    -1.16
     ftu
    -1.05
     effe
    -1.05
     poff
    -1.03
     tanga
    -1.03
     nece
    -1.02
     canel
    -1.02
     fta
    -1.01
     embodi
    -1.01
     carc
    -1.01
    POSITIVE LOGITS
     shares
    0.69
     shareholders
    0.66
     trading
    0.62
     share
    0.58
     stock
    0.58
     dividend
    0.57
    Shares
    0.57
     valuation
    0.56
     Shares
    0.56
     stockholders
    0.55
    Activations Density 0.197%

    No Known Activations