Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 8028
    Prev
    Next
    INDEX
    Explanations

    words related to prosthetics or parts of the body that are replaced by prosthetics

    oai_token-act-pair · gpt-3.5-turbo

    references to prosthetic devices

    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
    INESS
    -0.82
    Dick
    -0.77
     Bard
    -0.71
    hound
    -0.69
    EGIN
    -0.69
     Finder
    -0.67
    WAYS
    -0.67
    ÃĽ
    -0.67
     Bourbon
    -0.65
    Magikarp
    -0.64
    POSITIVE LOGITS
     prost
    1.30
    hetics
    1.21
    hetic
    1.08
    hesis
    1.00
    heses
    0.98
    orius
    0.98
    ificial
    0.90
    roleum
    0.87
    acet
    0.84
    rog
    0.83
    Activations Density 0.007%

    No Known Activations