© 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. 9042
    Prev
    Next
    INDEX
    Explanations

    phrases related to parking lots

    oai_token-act-pair · gpt-3.5-turbo

    mentions of parking lots and parking-related contexts

    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
    Downloadha
    -1.05
    xual
    -0.90
    gui
    -0.76
    akuya
    -0.72
    flix
    -0.69
    theless
    -0.67
    nces
    -0.66
    icz
    -0.66
     surg
    -0.65
    xus
    -0.65
    POSITIVE LOGITS
     garage
    1.13
    lot
    1.09
     Garage
    0.94
     attendants
    0.92
     spaces
    0.88
    conservancy
    0.85
     Lot
    0.83
     attendant
    0.82
     lot
    0.80
     brake
    0.80
    Activations Density 0.038%

    No Known Activations