© 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. 11-RES-JB
    11. 10085
    Prev
    Next
    INDEX
    Explanations

    economic and financial terms

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to economic decisions and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cknow
    -0.76
     Elias
    -0.65
     Together
    -0.65
    rote
    -0.64
    idav
    -0.63
     Correct
    -0.62
     Horowitz
    -0.62
    yk
    -0.62
    endum
    -0.61
    bold
    -0.61
    POSITIVE LOGITS
     attracts
    1.22
     tends
    1.16
     nowadays
    1.12
     deterior
    1.08
     seldom
    1.01
     scarce
    1.00
     costs
    1.00
     stagn
    0.99
     varies
    0.98
     doesnt
    0.97
    Activations Density 0.510%

    No Known Activations