© 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. 9-RES-JB
    11. 5079
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific body parts, such as 'knees' and 'ankles'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to injuries and health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thinking
    -0.81
     disrupting
    -0.71
    Calling
    -0.70
    Fla
    -0.67
     wary
    -0.67
     fearing
    -0.65
     skeptical
    -0.65
     waging
    -0.64
     dismissive
    -0.63
     dismissing
    -0.63
    POSITIVE LOGITS
     are
    1.51
     belong
    1.38
     consist
    1.36
     contain
    1.31
     were
    1.30
     vary
    1.23
     differ
    1.20
     ARE
    1.19
     aren
    1.19
     include
    1.18
    Activations Density 0.593%

    No Known Activations