© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 18842
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or occasions being hosted or organized by someone or a group

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "hosted."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    neg
    -0.84
    oro
    -0.76
    thur
    -0.76
    ocus
    -0.73
    vor
    -0.71
    wd
    -0.69
    imb
    -0.69
    esa
    -0.65
    ogn
    -0.64
    kes
    -0.64
    POSITIVE LOGITS
     hosted
    1.09
     hosting
    0.99
     host
    0.87
    Host
    0.84
     hosts
    0.79
     Host
    0.76
    host
    0.70
     guests
    0.70
     televised
    0.68
     presided
    0.66
    Activations Density 0.008%

    No Known Activations