© 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. 9-RES-JB
    11. 15737
    Prev
    Next
    INDEX
    Explanations

    proper names related to companies or brands

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names or brands, particularly those associated with news and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ares
    -0.89
    imir
    -0.85
    hens
    -0.84
    ork
    -0.74
    intosh
    -0.73
    iro
    -0.71
    ingly
    -0.71
    ĪĴ
    -0.70
    agna
    -0.69
    ery
    -0.68
    POSITIVE LOGITS
    glass
    0.74
    vier
    0.72
    ufact
    0.71
     Tou
    0.68
    ainer
    0.68
     Reuters
    0.66
    sonian
    0.65
    CLASS
    0.64
    baum
    0.64
    Charges
    0.64
    Activations Density 0.113%

    No Known Activations