© 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. 22313
    Prev
    Next
    INDEX
    Explanations

    words related to license plates

    oai_token-act-pair · gpt-3.5-turbo

    references to license plates

    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
    WIN
    -0.64
    yre
    -0.64
    zen
    -0.61
     league
    -0.61
     wedd
    -0.60
    ongo
    -0.59
     Rove
    -0.59
    onga
    -0.59
    cript
    -0.59
     career
    -0.59
    POSITIVE LOGITS
     plates
    3.78
    plates
    1.85
     dishes
    1.48
     discs
    1.38
     tables
    1.27
     disks
    1.25
     stickers
    1.24
     sheets
    1.22
     scrolls
    1.19
     shelves
    1.19
    Activations Density 0.020%

    No Known Activations