© 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. 7083
    Prev
    Next
    INDEX
    Explanations

    descriptions of luxurious locations, accommodation facilities, and related details

    oai_token-act-pair · gpt-3.5-turbo
    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
     clipboard
    -0.89
     vacc
    -0.86
    issors
    -0.84
    binary
    -0.81
     inoc
    -0.81
    ernel
    -0.79
    abwe
    -0.76
    unte
    -0.74
    ministic
    -0.72
     propagation
    -0.72
    POSITIVE LOGITS
     Hotel
    1.47
     Marriott
    1.45
     luxury
    1.41
     upscale
    1.39
     luxurious
    1.38
     Hilton
    1.37
     hotel
    1.34
     hotels
    1.31
     boutique
    1.30
     mansion
    1.24
    Activations Density 0.456%

    No Known Activations