© 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. 7645
    Prev
    Next
    INDEX
    Explanations

    references to the founding or construction of buildings or facilities

    oai_token-act-pair · gpt-3.5-turbo

    historical references and details related to buildings and their significance

    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
     particles
    -0.75
    azeera
    -0.72
    obin
    -0.71
     strokes
    -0.70
     grains
    -0.69
     flu
    -0.69
     flakes
    -0.68
     vectors
    -0.68
    gey
    -0.66
     strands
    -0.65
    POSITIVE LOGITS
     located
    1.29
     situated
    1.28
     Located
    1.26
     housed
    1.24
    Located
    1.18
     reopened
    1.12
     erected
    1.11
     renovated
    1.08
     operated
    1.08
    tyard
    1.08
    Activations Density 0.742%

    No Known Activations