© 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. 2783
    Prev
    Next
    INDEX
    Explanations

    terms related to wholesale

    oai_token-act-pair · gpt-3.5-turbo

    references to wholesale pricing

    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
    inguished
    -0.74
     Immunity
    -0.69
    Cam
    -0.69
    Med
    -0.68
    uder
    -0.67
    iazep
    -0.66
     orb
    -0.66
     Quad
    -0.64
    hib
    -0.64
    AF
    -0.64
    POSITIVE LOGITS
     wholesale
    3.91
     wholes
    1.36
     retail
    1.30
     outright
    1.18
     ware
    1.08
     Retail
    1.07
     distributors
    1.02
     distributor
    0.99
    merce
    0.97
     grocer
    0.97
    Activations Density 0.020%

    No Known Activations