© 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. 7708
    Prev
    Next
    INDEX
    Explanations

    instances of the word "parked"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "parked" and related terms, focusing on vehicles and their locations

    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
    é¾įå¥ij士
    -0.77
    bits
    -0.66
    ulkan
    -0.65
    ãĤ¡
    -0.64
    bern
    -0.64
     overload
    -0.64
     squared
    -0.64
    fax
    -0.62
    BIT
    -0.61
    idian
    -0.60
    POSITIVE LOGITS
     atop
    0.91
    river
    0.83
    arius
    0.78
    edIn
    0.76
     somewhere
    0.75
     beside
    0.74
    entary
    0.73
     parked
    0.72
     onto
    0.71
     peacefully
    0.71
    Activations Density 0.138%

    No Known Activations