© 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. 10-RES-JB
    11. 6626
    Prev
    Next
    INDEX
    Explanations

    website URLs in the form of http links

    oai_token-act-pair · gpt-3.5-turbo

    instances of reported events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lections
    -0.79
     ageing
    -0.74
     citiz
    -0.69
     compe
    -0.67
     newcom
    -0.67
    bourg
    -0.64
    minist
    -0.64
     tremend
    -0.62
     aging
    -0.61
     favoured
    -0.61
    POSITIVE LOGITS
    PHOTOS
    1.09
    SPONSORED
    0.91
    NPR
    0.84
    RELATED
    0.83
    Shape
    0.80
    Update
    0.79
    Original
    0.77
    Els
    0.77
    Scroll
    0.75
    UPDATE
    0.74
    Activations Density 0.432%

    No Known Activations