© 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. 427
    Prev
    Next
    INDEX
    Explanations

    phrases related to professions and tasks, with an emphasis on design, development, and management roles

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various professional roles and occupations

    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
     Sunrise
    -0.76
    jri
    -0.73
    ometown
    -0.65
    Accessory
    -0.63
    Reloaded
    -0.62
     Valkyrie
    -0.62
    TPS
    -0.60
    Las
    -0.59
    Aw
    -0.59
     Prosper
    -0.59
    POSITIVE LOGITS
    hip
    1.03
    hips
    0.92
     alike
    0.91
     everywhere
    0.90
     perceive
    0.90
     adhere
    0.89
     strive
    0.89
     communicate
    0.86
     realize
    0.86
    paces
    0.85
    Activations Density 0.370%

    No Known Activations