© 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. 1-RES-JB
    11. 20032
    Prev
    Next
    INDEX
    Explanations

    phrases related to business or financial activities, particularly bankruptcy or disruption

    oai_token-act-pair · gpt-3.5-turbo

    references to financial concepts related to bankruptcy and disruption

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shades
    -0.77
    ById
    -0.74
     thirds
    -0.72
    sie
    -0.64
     Thumbnails
    -0.63
     COP
    -0.63
    omething
    -0.61
    ITNESS
    -0.60
    friends
    -0.60
     compact
    -0.60
    POSITIVE LOGITS
    itent
    1.01
    oulos
    0.95
    rup
    0.93
    oples
    0.92
    culation
    0.90
    asar
    0.89
    owder
    0.89
    odcast
    0.89
    ovi
    0.89
    secution
    0.87
    Activations Density 0.014%

    No Known Activations