© 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. 2523
    Prev
    Next
    INDEX
    Explanations

    phrases related to business events and promotions

    oai_token-act-pair · gpt-3.5-turbo

    unique brand names and specialized terms related to specific organizations or products

    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
    oufl
    -0.73
    thens
    -0.73
     Zub
    -0.71
    orsche
    -0.70
    romeda
    -0.68
    nv
    -0.67
     Zhao
    -0.65
     Rah
    -0.63
    irmed
    -0.63
     Ago
    -0.63
    POSITIVE LOGITS
    Wiki
    0.88
     Magazine
    0.85
    Nation
    0.85
     Forums
    0.82
     Productions
    0.79
     Community
    0.78
    iverse
    0.78
     community
    0.78
     Presents
    0.76
     Nation
    0.75
    Activations Density 0.505%

    No Known Activations