© 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. 10-RES-JB
    11. 24551
    Prev
    Next
    INDEX
    Explanations

    prices and discounts represented in a specific format with currency symbols and decimal points

    oai_token-act-pair · gpt-3.5-turbo

    monetary values or price listings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pregn
    -0.69
     epidem
    -0.67
     typh
    -0.62
     apart
    -0.60
     organism
    -0.59
     soil
    -0.59
     cortisol
    -0.59
     auxiliary
    -0.57
     enthusi
    -0.57
     dred
    -0.56
    POSITIVE LOGITS
    99
    1.57
    95
    1.57
    00
    1.40
    50
    1.32
    75
    1.22
    98
    1.15
    90
    1.14
    60
    1.13
    85
    1.13
    49
    1.13
    Activations Density 0.041%

    No Known Activations