© 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. 0-RES-JB
    11. 5140
    Prev
    Next
    INDEX
    Explanations

    the word "hosting" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the act of hosting events or activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rait
    -0.69
    ought
    -0.66
    Lev
    -0.64
    ggle
    -0.63
    Effect
    -0.63
     instinctively
    -0.63
    Det
    -0.62
    legraph
    -0.62
     undone
    -0.62
    lt
    -0.62
    POSITIVE LOGITS
     hosting
    3.83
     hosted
    2.14
     hosts
    2.10
     host
    1.99
     sponsoring
    1.81
    host
    1.77
    Host
    1.74
     Host
    1.74
     staging
    1.41
     organising
    1.40
    Activations Density 0.009%

    No Known Activations