© 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. 20273
    Prev
    Next
    INDEX
    Explanations

    words related to construction and establishment of physical structures

    oai_token-act-pair · gpt-3.5-turbo

    actions related to construction, creation, or establishment of entities

    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
    yip
    -0.61
    bara
    -0.60
    pires
    -0.60
    chair
    -0.57
    rium
    -0.57
    something
    -0.57
     Shack
    -0.55
    Ru
    -0.55
     itself
    -0.55
    someone
    -0.54
    POSITIVE LOGITS
     individually
    1.10
     throughout
    0.94
     separately
    0.94
     consecut
    0.93
     collectively
    0.87
    abouts
    0.84
     simultaneously
    0.84
     together
    0.84
     apiece
    0.81
     concurrently
    0.80
    Activations Density 0.385%

    No Known Activations