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

    Neuronpedia

    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. 11-RES-JB
    11. 20376
    Prev
    Next
    INDEX
    Explanations

    words related to financial terms such as "comments", "debtors", and "bonuses"

    oai_token-act-pair · gpt-3.5-turbo

    key financial and regulatory terms connected to analysis and assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     srfAttach
    -0.78
    cffffcc
    -0.78
    doesn
    -0.67
    stop
    -0.63
    Weak
    -0.63
     havoc
    -0.59
    PHOTOS
    -0.59
    lier
    -0.58
    volent
    -0.57
    ordinate
    -0.57
    POSITIVE LOGITS
     utilized
    1.41
     obtained
    1.38
     undertaken
    1.35
     submitted
    1.33
     presented
    1.31
     performed
    1.30
     received
    1.29
     achieved
    1.28
     encountered
    1.28
     executed
    1.25
    Activations Density 0.688%

    No Known Activations