© 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. 8-RES-JB
    11. 17094
    Prev
    Next
    INDEX
    Explanations

    URL image paths common in web development

    oai_token-act-pair · gpt-3.5-turbo

    elements related to web content and file uploads

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Survivors
    -0.73
    imity
    -0.72
     Addiction
    -0.71
     caveats
    -0.71
     Recomm
    -0.71
     abstinence
    -0.71
    ¯¯¯¯
    -0.69
     reservations
    -0.69
     Ethics
    -0.66
     practition
    -0.65
    POSITIVE LOGITS
    cdn
    1.28
    images
    1.28
    img
    1.21
    jpg
    1.13
    uploads
    1.04
    usercontent
    1.03
    icons
    1.01
    assets
    0.98
    photos
    0.94
    phot
    0.93
    Activations Density 0.097%

    No Known Activations