© 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. 3330
    Prev
    Next
    INDEX
    Explanations

    common mistakes made by people in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to common mistakes or errors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    atform
    -0.80
    iterranean
    -0.77
    ropolitan
    -0.75
    irming
    -0.75
    ript
    -0.73
    izons
    -0.70
    Recomm
    -0.68
     inclusive
    -0.68
     unity
    -0.68
    markets
    -0.67
    POSITIVE LOGITS
     accidentally
    1.17
     mishand
    1.17
     careless
    1.10
     unintentionally
    1.09
     inadvert
    1.06
     mistakes
    1.05
     improperly
    1.02
     unintended
    0.99
     unfortunate
    0.98
     injure
    0.98
    Activations Density 1.008%

    No Known Activations