© 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. 10640
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to financial matters or capital investments

    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
    674
    +0.14
    0.4%
    872
    +0.12
    0.3%
    381
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    872
    +0.14
    0.06
    71
    +0.12
    0.02
    1383
    +0.10
    0.03
    Negative Logits
     lemp
    -0.99
     lele
    -0.92
     hcm
    -0.89
     hina
    -0.89
    arture
    -0.88
     Telex
    -0.82
     kasa
    -0.81
     gend
    -0.81
     parati
    -0.80
     dises
    -0.79
    POSITIVE LOGITS
     answer
    1.06
     answers
    0.98
     answered
    0.95
    answer
    0.92
     Answer
    0.91
    Answer
    0.87
    Answers
    0.86
    <bos>
    0.84
     Answers
    0.83
     answering
    0.83
    Activations Density 0.397%

    No Known Activations