© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 22829
    Prev
    Next
    INDEX
    Explanations

    structured sentences that start with "So", "But", "When", "Help", "Ask", "It", "This", "However", "An", "In", "You", "Let's", or " The"

    oai_token-act-pair · gpt-3.5-turbo

    references to challenges or difficulties in professional or organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abouts
    -0.74
     gunned
    -0.71
     promptly
    -0.67
     embattled
    -0.67
     interim
    -0.66
    ussia
    -0.65
     footing
    -0.64
     bung
    -0.64
     marching
    -0.63
     hung
    -0.62
    POSITIVE LOGITS
    ³³³³³³³³
    1.07
    ³³³
    1.05
    ³³³³
    1.04
    ³³³³³³³³³³³³³³³³
    1.04
    Example
    0.98
    Therefore
    0.98
    Learn
    0.96
    Understanding
    0.92
    Solution
    0.91
    Examples
    0.89
    Activations Density 0.395%

    No Known Activations