© 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. 6504
    Prev
    Next
    INDEX
    Explanations

    the word "Hollow" or similar variations in the text

    oai_token-act-pair · gpt-3.5-turbo

    the term "hollow" and its various usages and contexts

    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
    manship
    -0.86
    BIL
    -0.78
    xual
    -0.74
    minist
    -0.69
    ional
    -0.69
    HAHAHAHA
    -0.68
    uana
    -0.67
    BILITY
    -0.66
    BILITIES
    -0.65
    iveness
    -0.65
    POSITIVE LOGITS
    een
    0.88
    odon
    0.85
    utonium
    0.79
     Bore
    0.77
    erton
    0.76
    blade
    0.75
    nuts
    0.71
    ossom
    0.71
    fish
    0.70
    erd
    0.70
    Activations Density 0.082%

    No Known Activations