© 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. 769
    Prev
    Next
    INDEX
    Explanations

    mentions of proper names, potentially related to interviews or profiles

    oai_token-act-pair · gpt-3.5-turbo

    the letter "G" at the beginning of various words or phrases

    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
    ĸļ
    -0.75
     derail
    -0.62
     compr
    -0.62
     Mellon
    -0.58
     parted
    -0.58
     reprodu
    -0.58
     htt
    -0.58
    puter
    -0.57
     craw
    -0.57
    terday
    -0.56
    POSITIVE LOGITS
    roups
    1.35
    raphic
    1.30
    reetings
    1.22
    ourmet
    1.18
    ossip
    1.17
    reens
    1.16
    irlfriend
    1.15
    iants
    1.15
    AMES
    1.14
    uild
    1.13
    Activations Density 0.048%

    No Known Activations