© 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. 6879
    Prev
    Next
    INDEX
    Explanations

    prices or pricing information in texts

    oai_token-act-pair · gpt-3.5-turbo

    references to pricing and pricing strategies

    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
     Survivors
    -0.65
    ious
    -0.61
    wart
    -0.60
    asm
    -0.58
     Reich
    -0.58
     corpus
    -0.57
    ion
    -0.56
     associations
    -0.56
    arella
    -0.56
    iot
    -0.56
    POSITIVE LOGITS
     priced
    4.01
    priced
    2.41
     pricing
    1.82
     Pricing
    1.67
    price
    1.66
     pric
    1.59
     Pric
    1.57
     price
    1.54
     prices
    1.54
     costing
    1.50
    Activations Density 0.011%

    No Known Activations