© 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. 0-RES-JB
    11. 2872
    Prev
    Next
    INDEX
    Explanations

    numeric values related to square footage

    oai_token-act-pair · gpt-3.5-turbo

    mentions of square footage or area measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Quin
    -0.72
     Izan
    -0.65
     alloc
    -0.64
     lasted
    -0.62
     legalized
    -0.62
     à¤
    -0.62
     coales
    -0.58
     biased
    -0.57
     Cards
    -0.57
     glac
    -0.57
    POSITIVE LOGITS
    ft
    4.54
    fts
    3.19
     ft
    2.11
    ften
    2.07
    FT
    1.87
    fty
    1.65
    aft
    1.57
    feet
    1.33
    lf
    1.29
    ff
    1.23
    Activations Density 0.013%

    No Known Activations