© 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. 11-RES-JB
    11. 7067
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the number of games or trips taken

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating recent performance or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hyde
    -0.71
    conom
    -0.58
     Background
    -0.58
    issance
    -0.57
    mund
    -0.53
    EStreamFrame
    -0.52
     Terrorism
    -0.52
    clerosis
    -0.51
     Moder
    -0.51
    oller
    -0.50
    POSITIVE LOGITS
     two
    1.25
     four
    1.25
     three
    1.24
     eight
    1.20
     five
    1.19
     seven
    1.18
     nine
    1.16
     six
    1.14
     eleven
    1.04
     twelve
    1.03
    Activations Density 0.089%

    No Known Activations