© 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. 6-RES-JB
    11. 13600
    Prev
    Next
    INDEX
    Explanations

    phrases related to old-school or traditional style or methods

    oai_token-act-pair · gpt-3.5-turbo

    references to traditional or retro styles and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eeper
    -0.76
    abases
    -0.73
    osuke
    -0.72
    leased
    -0.71
    aughters
    -0.71
    borough
    -0.70
    pta
    -0.70
    SPONSORED
    -0.69
    osher
    -0.69
    quet
    -0.69
    POSITIVE LOGITS
    fashioned
    0.94
     elegance
    0.90
     fashioned
    0.87
     Revival
    0.86
     charm
    0.82
     style
    0.78
     nostalgia
    0.74
     analog
    0.74
     classic
    0.74
     wisdom
    0.71
    Activations Density 0.043%

    No Known Activations