© 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. 3-RES-JB
    11. 6415
    Prev
    Next
    INDEX
    Explanations

    words related to image processing and medical conditions

    oai_token-act-pair · gpt-3.5-turbo

    technical terms and jargon related to scientific or medical contexts

    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
     Fey
    -0.57
     Shutterstock
    -0.53
     Dragonbound
    -0.52
     Kills
    -0.50
     anecdotes
    -0.49
     largeDownload
    -0.49
    cember
    -0.49
     Purple
    -0.49
     imagination
    -0.48
     dearly
    -0.47
    POSITIVE LOGITS
    enced
    0.79
    oped
    0.74
    agog
    0.71
    ader
    0.71
    ret
    0.70
    iped
    0.68
    ission
    0.68
    ased
    0.67
    action
    0.65
    icative
    0.65
    Activations Density 0.440%

    No Known Activations