© 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. 9273
    Prev
    Next
    INDEX
    Explanations

    phrases related to mental health, specifically focusing on terms associated with extreme behavior or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of "lunacy" or madness

    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
    âĢ¢âĢ¢
    -0.75
    LECT
    -0.67
     Lot
    -0.67
    ORD
    -0.66
    ORN
    -0.66
     NRS
    -0.64
     Sr
    -0.60
     depos
    -0.60
     Seymour
    -0.57
     Swan
    -0.56
    POSITIVE LOGITS
    cheon
    1.63
    atic
    1.50
    atics
    1.50
    acy
    1.42
    atical
    1.20
    ches
    1.20
    etic
    1.10
    atown
    1.08
    acies
    1.08
    atically
    1.07
    Activations Density 0.053%

    No Known Activations