© 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. 7-RES-JB
    11. 2182
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to challenging situations or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to difficulties and challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    riter
    -0.74
    irie
    -0.67
    Rate
    -0.66
    eor
    -0.65
    nesty
    -0.65
    flag
    -0.64
    orks
    -0.64
    ificantly
    -0.64
    Table
    -0.63
    erville
    -0.63
    POSITIVE LOGITS
     slog
    1.10
     navigating
    0.97
     juggling
    0.95
     balancing
    0.92
     daunting
    0.91
     chore
    0.89
     uphill
    0.82
     gru
    0.82
     ordeal
    0.81
     figuring
    0.80
    Activations Density 0.319%

    No Known Activations