© 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. 11-RES-JB
    11. 7803
    Prev
    Next
    INDEX
    Explanations

    medical or injury-related terms and experiences

    oai_token-act-pair · gpt-3.5-turbo

    intense emotional experiences related to trauma or distress

    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
    awei
    -0.83
    ospons
    -0.80
    ranch
    -0.80
    advertising
    -0.79
     Funding
    -0.69
     endorsements
    -0.68
     endors
    -0.67
    worthiness
    -0.67
    saf
    -0.67
    venue
    -0.66
    POSITIVE LOGITS
     numb
    1.38
     tears
    1.30
     panic
    1.26
     flashbacks
    1.26
     halluc
    1.26
     adrenaline
    1.25
     lucid
    1.24
     sob
    1.23
     orgasm
    1.23
     consciousness
    1.22
    Activations Density 0.462%

    No Known Activations