© 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. 1-RES-JB
    11. 23227
    Prev
    Next
    INDEX
    Explanations

    website widgets, particularly those related to marketing campaigns or ads

    oai_token-act-pair · gpt-3.5-turbo

    references to specific products or items, particularly "widgets."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    panic
    -0.81
    dinand
    -0.80
    rano
    -0.76
    rule
    -0.76
    rity
    -0.75
    enic
    -0.70
    chal
    -0.69
    pine
    -0.68
    nings
    -0.67
    vo
    -0.67
    POSITIVE LOGITS
     widget
    1.45
    widget
    1.44
     widgets
    1.31
    Widget
    1.14
    idget
    1.09
    zilla
    0.92
     drawer
    0.81
    Kit
    0.79
     toolbar
    0.74
     calendar
    0.73
    Activations Density 0.012%

    No Known Activations