© 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. 20277
    Prev
    Next
    INDEX
    Explanations

    information related to changes in prices, rates, and policies

    oai_token-act-pair · gpt-3.5-turbo

    financial terms and indicators related to costs, fees, and taxes

    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
    nsics
    -0.82
     Laden
    -0.79
     Syndrome
    -0.75
     Virus
    -0.74
     paranormal
    -0.71
     archae
    -0.70
    orno
    -0.68
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.68
     histor
    -0.67
     Tears
    -0.67
    POSITIVE LOGITS
     phased
    1.33
     rebate
    1.28
     levy
    1.26
     discounts
    1.22
     reductions
    1.21
     capped
    1.21
     allowances
    1.20
     increments
    1.17
     subsidy
    1.17
     savings
    1.16
    Activations Density 0.448%

    No Known Activations