© 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. 8-RES-JB
    11. 3344
    Prev
    Next
    INDEX
    Explanations

    references to individuals with medical degrees (MD) and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to medical degrees and titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nel
    -0.78
    stall
    -0.78
    stal
    -0.71
    lio
    -0.70
     LAPD
    -0.69
    nder
    -0.68
    glers
    -0.66
    asonable
    -0.66
     appet
    -0.65
    cluded
    -0.64
    POSITIVE LOGITS
    iamond
    1.13
    ouble
    0.96
    IVER
    0.90
    aughter
    0.88
    iate
    0.81
    ARS
    0.80
    ART
    0.80
    etermination
    0.79
    ODE
    0.78
    ULT
    0.78
    Activations Density 0.039%

    No Known Activations