© 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. 4882
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations or entities such as "Feet Under," "Corn," "Speed," "Command," "One," "Dog," "Wishes," "leaf," "Loko," "Day," "eleven," "Gun," "Thirds," "Courts," and "

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to titles and themes from various media and cultural references

    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
    uga
    -0.69
    escription
    -0.67
    livious
    -0.65
    aldehyde
    -0.62
     Kimmel
    -0.62
    etsk
    -0.61
    External
    -0.61
    Protect
    -0.60
    اÙĦ
    -0.60
    Public
    -0.59
    POSITIVE LOGITS
    undred
    1.03
    ighters
    0.83
    ousand
    0.75
    ths
    0.72
    secut
    0.71
     Wonders
    0.71
     Brewing
    0.69
    isan
    0.69
    gged
    0.68
    ighter
    0.68
    Activations Density 0.217%

    No Known Activations