© 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. 6757
    Prev
    Next
    INDEX
    Explanations

    personal experiences and emotions related to trauma and abuse

    oai_token-act-pair · gpt-3.5-turbo

    references to personal trauma and experiences related to abuse

    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
    yip
    -0.71
    `.
    -0.69
    ranch
    -0.68
    »
    -0.67
     ®
    -0.66
     sidx
    -0.66
    mercial
    -0.63
    ãĥ¢
    -0.63
     Exec
    -0.62
     Thumbnails
    -0.62
    POSITIVE LOGITS
     myself
    1.24
     my
    1.22
     classmates
    1.09
     puberty
    1.08
     adulthood
    1.08
     friendships
    1.02
     therapists
    1.01
     adolescence
    1.01
     therapist
    1.00
     dysph
    1.00
    Activations Density 0.839%

    No Known Activations