© 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. 6-RES-JB
    11. 7934
    Prev
    Next
    INDEX
    Explanations

    medical and health-related terms or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health issues and financial troubles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pixel
    -0.66
     Zur
    -0.62
     Universe
    -0.62
    ICLE
    -0.62
    ulhu
    -0.61
     Logo
    -0.59
     Streets
    -0.58
     Instant
    -0.58
    ghai
    -0.57
     Macro
    -0.57
    POSITIVE LOGITS
     duties
    0.85
     advis
    0.85
     withdrawals
    0.84
     reservations
    0.83
     irregularities
    0.83
     arrangements
    0.81
     eligibility
    0.77
     enhancements
    0.77
     contention
    0.75
     difficulties
    0.75
    Activations Density 0.645%

    No Known Activations