© 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. 11-RES-JB
    11. 3635
    Prev
    Next
    INDEX
    Explanations

    terms related to medical/psychiatric conditions like depression, stress-coping styles, anxiety, and physiological effects

    oai_token-act-pair · gpt-3.5-turbo

    terms related to psychiatric disorders and their effects

    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
    wered
    -0.76
     ain
    -0.63
     Mehran
    -0.60
    doesn
    -0.60
    TextColor
    -0.59
     isn
    -0.58
     Dirt
    -0.58
    CLASSIFIED
    -0.57
     whats
    -0.57
     roared
    -0.57
    POSITIVE LOGITS
     ().
    1.40
     (),
    1.12
     ([
    1.10
     (>
    1.09
     (âĪĴ
    1.07
     âĪ¼
    1.05
     (<
    1.03
    .–
    0.99
     mediated
    0.98
     [(
    0.96
    Activations Density 0.576%

    No Known Activations