© 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. 23728
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "That's"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific character or symbol

    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
     Rag
    -0.70
     ropes
    -0.70
     horizont
    -0.67
     Agric
    -0.64
     Marshal
    -0.62
     snacks
    -0.61
     sacrific
    -0.61
     gad
    -0.60
    Buyable
    -0.59
     snack
    -0.58
    POSITIVE LOGITS
    º
    1.05
    Ĵ
    0.99
    ¹
    0.96
    ¡
    0.95
    ķ
    0.93
    £
    0.92
    ®
    0.87
    ¼
    0.86
    certain
    0.83
    ĵ
    0.83
    Activations Density 0.045%

    No Known Activations