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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3109
    Prev
    Next
    INDEX
    Explanations

    phrases related to hub or hubris

    oai_token-act-pair · gpt-3.5-turbo

    references to various hubs or central points in a context

    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
    terday
    -0.69
    izations
    -0.68
    anguage
    -0.67
     graded
    -0.67
     Grave
    -0.66
    ists
    -0.65
    IGHTS
    -0.65
     Jackets
    -0.65
    izable
    -0.64
     Chatt
    -0.62
    POSITIVE LOGITS
    bub
    1.48
    bard
    1.33
    ris
    1.08
    lins
    1.04
    hub
    1.02
    staff
    1.02
    bies
    1.02
    lot
    0.98
    Hub
    0.97
    bie
    0.95
    Activations Density 0.027%

    No Known Activations