© 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. 16433
    Prev
    Next
    INDEX
    Explanations

    phrases related to service providers

    oai_token-act-pair · gpt-3.5-turbo
    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
    lees
    -1.15
     Governments
    -1.13
     presidents
    -1.08
     governments
    -1.06
     churches
    -1.05
     minorities
    -1.05
     colleges
    -1.03
     groups
    -1.02
     Muslims
    -1.01
     Presidents
    -1.01
    POSITIVE LOGITS
     provider
    1.96
     manufacturer
    1.77
     supplier
    1.70
     maker
    1.65
     lender
    1.57
     retailer
    1.56
     distributor
    1.55
     operator
    1.49
     insurer
    1.47
     publisher
    1.35
    Activations Density 0.054%

    No Known Activations