© 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. 10-RES-JB
    11. 17389
    Prev
    Next
    INDEX
    Explanations

    phrases related to support or endorsement of a cause or effort

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to support and inspiration in a community context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gow
    -0.79
    mania
    -0.73
     Iro
    -0.66
    lication
    -0.66
     Presumably
    -0.62
    naire
    -0.61
    lda
    -0.60
    ciation
    -0.60
     GC
    -0.59
     interchange
    -0.59
    POSITIVE LOGITS
     journalism
    1.01
    iframe
    0.93
    utenberg
    0.87
     Journalism
    0.85
    Content
    0.82
     readers
    0.82
     editorial
    0.82
     Marketplace
    0.81
     Subscribe
    0.80
     Stories
    0.78
    Activations Density 0.111%

    No Known Activations