© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17848
    Prev
    Next
    INDEX
    Explanations

    mentions of museums

    oai_token-act-pair · gpt-3.5-turbo

    references to museums

    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
    nir
    -0.87
    shaw
    -0.66
    lees
    -0.64
    ---------
    -0.64
    maxwell
    -0.62
    Leary
    -0.62
    ulf
    -0.62
    iated
    -0.61
    yip
    -0.60
    LAN
    -0.59
    POSITIVE LOGITS
    useum
    1.03
    ĸļ
    1.00
     curator
    0.96
     museum
    0.88
    arium
    0.86
     museums
    0.85
     exhibits
    0.85
     galleries
    0.80
     exhibitions
    0.78
    arch
    0.77
    Activations Density 0.030%

    No Known Activations