© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18487
    Prev
    Next
    INDEX
    Explanations

    references to activities or items related to being at home

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "home" or related places

    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
    ratulations
    -0.62
    zhen
    -0.58
    sylv
    -0.58
     choir
    -0.57
     Peb
    -0.57
     Patriarch
    -0.56
     Duff
    -0.56
    anson
    -0.55
     spores
    -0.54
    ERY
    -0.54
    POSITIVE LOGITS
     behest
    0.99
     glance
    0.89
     expense
    0.87
     discretion
    0.84
     disposal
    0.83
    Footnote
    0.79
     helm
    0.76
     intersections
    0.74
     apiece
    0.71
     outset
    0.69
    Activations Density 0.212%

    No Known Activations