© 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. 6-RES-JB
    11. 11624
    Prev
    Next
    INDEX
    Explanations

    words related to taxi services

    oai_token-act-pair · gpt-3.5-turbo

    references to taxi services and operators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -1.00
    natureconservancy
    -0.80
    utz
    -0.75
    isite
    -0.72
    vironment
    -0.72
    maxwell
    -0.72
    wart
    -0.71
    cius
    -0.69
    mberg
    -0.69
    DonaldTrump
    -0.68
    POSITIVE LOGITS
     cab
    0.92
     taxi
    0.88
    bay
    0.82
     rides
    0.82
     courier
    0.81
     drivers
    0.80
     taxis
    0.79
    aret
    0.76
     ride
    0.75
    ways
    0.75
    Activations Density 0.017%

    No Known Activations