© 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. 9-RES-JB
    11. 16356
    Prev
    Next
    INDEX
    Explanations

    references to a specific location or point of return in the text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating navigation or direction

    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
    aneously
    -0.73
    76561
    -0.72
    cially
    -0.70
    ssh
    -0.70
    arily
    -0.66
    oan
    -0.65
    ãĥı
    -0.65
    iating
    -0.65
    é¾įåĸļ士
    -0.64
    ographically
    -0.64
    POSITIVE LOGITS
     Gallery
    0.98
     Contents
    0.91
     Top
    0.88
     TOP
    0.83
     Blog
    0.80
     top
    0.79
     Menu
    0.79
     Main
    0.73
     Bottom
    0.72
     Index
    0.70
    Activations Density 0.033%

    No Known Activations