© 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. 7429
    Prev
    Next
    INDEX
    Explanations

    mentions of rehabilitation or rehab-related activities

    oai_token-act-pair · gpt-3.5-turbo

    references to rehabilitation and rehab-related contexts

    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
     Flan
    -0.75
    Dad
    -0.66
     Hollande
    -0.65
    anto
    -0.64
    DN
    -0.63
     Noir
    -0.63
     Wilde
    -0.61
    anza
    -0.61
     Coulter
    -0.58
     horn
    -0.57
    POSITIVE LOGITS
    ilitating
    1.76
    ilitation
    1.75
    apist
    1.04
    ilit
    1.04
    bing
    1.02
    spective
    1.00
     rehabilitation
    0.97
     rehab
    0.94
     Rehab
    0.94
    yrinth
    0.90
    Activations Density 0.009%

    No Known Activations