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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4-RES-JB
    11. 6357
    Prev
    Next
    INDEX
    Explanations

    words related to bones or bone-related medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to bone health and conditions

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

    No Comments

    Negative Logits
    eanor
    -0.80
    entric
    -0.74
     Policies
    -0.73
    olitan
    -0.72
    sers
    -0.71
    PLIED
    -0.71
    atcher
    -0.70
    committee
    -0.69
     Editorial
    -0.68
     Emerging
    -0.67
    POSITIVE LOGITS
     marrow
    1.65
    Bone
    1.22
    bone
    1.20
    bones
    1.14
     fide
    1.08
     bones
    1.02
     bone
    0.95
    headed
    0.95
    meal
    0.92
    heads
    0.92
    Activations Density 0.008%

    No Known Activations