© 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. 8-RES-JB
    11. 20460
    Prev
    Next
    INDEX
    Explanations

    references to various forms of payment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to online payment processing

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dresden
    -0.74
     Nare
    -0.70
     Scotia
    -0.68
    GGGGGGGG
    -0.68
    ^^^^
    -0.67
    KEN
    -0.66
     Frankfurt
    -0.65
     Uriel
    -0.64
    udic
    -0.61
     Kamp
    -0.61
    POSITIVE LOGITS
    outs
    1.29
    ments
    1.20
    back
    1.19
    roll
    1.17
    checks
    1.15
    offs
    1.09
    pal
    0.99
    backs
    0.98
    load
    0.95
    wall
    0.93
    Activations Density 0.036%

    No Known Activations