© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 6941
    Prev
    Next
    INDEX
    Explanations

    keywords related to financial investment and investigative reporting

    oai_token-act-pair · gpt-3.5-turbo

    terms related to investment and financial activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TEXTURE
    -0.73
     deaf
    -0.69
     lions
    -0.68
     Gemini
    -0.66
    PLE
    -0.64
    netflix
    -0.64
    Ļ½
    -0.63
     Paula
    -0.61
    ĪĴ
    -0.61
    xus
    -0.61
    POSITIVE LOGITS
    igating
    1.17
    iture
    1.17
    igation
    1.15
    ament
    1.14
    ments
    1.13
    iment
    1.12
    igator
    1.10
    ment
    1.09
    itures
    1.07
    iation
    1.07
    Activations Density 0.006%

    No Known Activations