© 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. 6696
    Prev
    Next
    INDEX
    Explanations

    words related to service providers, such as businesses or professionals offering specific services

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various service providers

    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
    inction
    -0.70
     LSD
    -0.70
    WAR
    -0.70
    rake
    -0.68
    Jew
    -0.68
    ————————————————
    -0.67
    ye
    -0.65
    lde
    -0.64
    sung
    -0.64
     Lud
    -0.64
    POSITIVE LOGITS
     providers
    3.51
     provider
    3.02
     Provider
    2.34
    Provider
    1.88
     suppliers
    1.71
     vendors
    1.50
     carriers
    1.49
     operators
    1.46
     clinicians
    1.37
     caregivers
    1.37
    Activations Density 0.026%

    No Known Activations