© 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. 10-RES-JB
    11. 9912
    Prev
    Next
    INDEX
    Explanations

    descriptions of various health-related scenarios and conditions, particularly those involving physical trauma or medical treatment

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trauma and its effects on victims

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Logo
    -0.78
     antitrust
    -0.76
     Franch
    -0.76
     Bezos
    -0.74
     Flags
    -0.72
     Sebast
    -0.70
     Fancy
    -0.70
     Funny
    -0.68
     Pirates
    -0.68
     Skies
    -0.68
    POSITIVE LOGITS
     traumat
    1.34
     caregivers
    1.32
     symptoms
    1.31
     relapse
    1.31
     careg
    1.28
     trauma
    1.27
     traumatic
    1.26
     untreated
    1.23
     psychologically
    1.23
     lifelong
    1.21
    Activations Density 0.508%

    No Known Activations