© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 16189
    Prev
    Next
    INDEX
    Explanations

    words related to joints and arthritis

    oai_token-act-pair · gpt-3.5-turbo

    references to joints and conditions related to joint health, particularly arthritis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BILITIES
    -0.72
    天
    -0.71
    cry
    -0.70
    opoulos
    -0.70
     RNA
    -0.65
     mainland
    -0.65
     Prel
    -0.65
     [|
    -0.65
     Mé
    -0.64
    cn
    -0.64
    POSITIVE LOGITS
     joints
    1.16
    ilage
    0.92
     jerk
    0.89
     joint
    0.89
    estinal
    0.87
     arthritis
    0.83
     throb
    0.81
    unction
    0.77
    roid
    0.77
    bing
    0.72
    Activations Density 0.010%

    No Known Activations