Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 4788
    Prev
    Next
    INDEX
    Explanations

    texts related to trauma and stress disorders, particularly post-traumatic stress disorder (PTSD)

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trauma and stress disorders

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    andr
    -0.88
    ebus
    -0.86
    arius
    -0.81
    eton
    -0.79
    ynthesis
    -0.77
    eva
    -0.75
    eller
    -0.74
    heit
    -0.74
    ells
    -0.73
    abet
    -0.72
    POSITIVE LOGITS
     traumatic
    1.03
    traumatic
    0.97
     nightmares
    0.87
     scars
    0.84
    umatic
    0.84
     memories
    0.83
     Stress
    0.81
     trauma
    0.80
     distress
    0.79
     stress
    0.77
    Activations Density 0.007%

    No Known Activations