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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16909
    Prev
    Next
    INDEX
    Explanations

    medical terminologies related to different diseases and conditions

    oai_token-act-pair · gpt-3.5-turbo

    medical terminology related to cancer and blood disorders

    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
     Grounds
    -0.79
    Dash
    -0.72
    Money
    -0.71
     Fool
    -0.68
     rooft
    -0.67
     Money
    -0.66
     Country
    -0.65
     Yard
    -0.65
    ãĤ±
    -0.64
     Legends
    -0.64
    POSITIVE LOGITS
    ogenesis
    1.16
    emia
    1.11
    ogenic
    1.11
    osis
    1.09
    ectomy
    1.03
    otropic
    1.02
    otyp
    1.02
    asis
    1.01
    iasis
    1.01
    ophys
    0.99
    Activations Density 0.168%

    No Known Activations