© 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. 22515
    Prev
    Next
    INDEX
    Explanations

    phrases related to addressing important issues or concerns

    oai_token-act-pair · gpt-3.5-turbo

    repeated or marked symbols, likely indicating formatting or special characters in the text

    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
     pleasures
    -0.72
     presets
    -0.67
     jugg
    -0.67
     shape
    -0.66
     warr
    -0.66
     seiz
    -0.65
     downs
    -0.65
     habit
    -0.64
     snail
    -0.64
     flavour
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.05
    efe
    0.93
    ONSORED
    0.87
    said
    0.81
    âĢİ
    0.78
    However
    0.77
     Similarly
    0.76
    raising
    0.76
    his
    0.76
    ¯
    0.75
    Activations Density 0.218%

    No Known Activations