© 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 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. 5360
    Prev
    Next
    INDEX
    Explanations

    financial and wealth-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
    964
    +0.14
    0.4%
    1533
    +0.12
    0.3%
    198
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1533
    +0.14
    0.02
    1135
    +0.12
    0.03
    964
    +0.11
    0.04
    Negative Logits
     revan
    -0.82
     frau
    -0.80
     hek
    -0.80
     kram
    -0.79
     indestru
    -0.78
     peculi
    -0.78
     elek
    -0.77
     tyn
    -0.74
     traktor
    -0.74
     disreg
    -0.74
    POSITIVE LOGITS
    <bos>
    0.74
     childhood
    0.62
     upbringing
    0.60
     grew
    0.55
    ⓧ
    0.52
    iyle
    0.51
     early
    0.49
    early
    0.48
    /**
    0.48
     carregar
    0.48
    Activations Density 0.378%

    No Known Activations