© 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. 20359
    Prev
    Next
    INDEX
    Explanations

    prices and quantities related to food items

    oai_token-act-pair · gpt-3.5-turbo

    monetary values and price-related information

    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
     appellate
    -0.69
    eatures
    -0.67
     livest
    -0.66
     headlined
    -0.65
    paralle
    -0.63
    aneers
    -0.62
    sembly
    -0.61
    £ı
    -0.60
     polyg
    -0.60
     abound
    -0.60
    POSITIVE LOGITS
     0
    2.19
    0
    1.77
     è£ıè¦ļéĨĴ
    1.01
     1
    1.00
     000
    1.00
     âĪĴ
    0.97
    isSpecialOrderable
    0.91
     zero
    0.88
     0004
    0.86
    048
    0.85
    Activations Density 0.099%

    No Known Activations