© 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. 6797
    Prev
    Next
    INDEX
    Explanations

    references to the location "Manhattan."

    oai_token-act-pair · gpt-3.5-turbo

    references to Manhattan

    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
    ional
    -0.88
    ioned
    -0.82
    ivia
    -0.80
    np
    -0.79
    inen
    -0.79
    utic
    -0.76
    ive
    -0.75
    vo
    -0.74
    fully
    -0.73
    milo
    -0.72
    POSITIVE LOGITS
     borough
    1.19
     Borough
    1.16
     skysc
    0.96
     skyline
    0.94
     Beach
    0.92
     apartment
    0.84
     Projects
    0.83
     subway
    0.83
     Island
    0.79
     Jets
    0.79
    Activations Density 0.074%

    No Known Activations