© 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. 0-RES-JB
    11. 11716
    Prev
    Next
    INDEX
    Explanations

    terms related to human body joints and related conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to joint-related issues and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hunt
    -0.72
     Wol
    -0.67
    Sav
    -0.65
    iren
    -0.65
    Reporting
    -0.65
     Refugee
    -0.64
     Sanford
    -0.63
    rina
    -0.63
    alker
    -0.62
    storm
    -0.62
    POSITIVE LOGITS
     joints
    4.23
     joint
    2.20
     Joint
    1.56
     arthritis
    1.54
     ribs
    1.47
     ankles
    1.36
     seams
    1.33
     elbows
    1.30
     bones
    1.23
     limbs
    1.22
    Activations Density 0.021%

    No Known Activations