© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10063
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial practices and services

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to financial burdens and deceptive practices

    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
    ahime
    -0.77
     Osw
    -0.74
     composure
    -0.67
    igm
    -0.66
     unity
    -0.66
     Pie
    -0.65
     unification
    -0.64
    nesota
    -0.63
    atform
    -0.62
     Redd
    -0.61
    POSITIVE LOGITS
     bogus
    1.34
     phony
    1.21
     illegally
    1.15
     falsely
    1.14
     worthless
    1.12
     ineligible
    1.11
     dubious
    1.10
     inferior
    1.09
     unrealistic
    1.07
     inflated
    1.07
    Activations Density 0.698%

    No Known Activations