© 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. 1-RES-JB
    11. 7598
    Prev
    Next
    INDEX
    Explanations

    references to diaspora communities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of diaspora and related terms

    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
    ered
    -0.76
    nered
    -0.75
    headed
    -0.75
     predetermined
    -0.68
    ses
    -0.65
    iet
    -0.64
     Sleeping
    -0.61
     presumption
    -0.61
    ezvous
    -0.61
    erm
    -0.61
    POSITIVE LOGITS
    pora
    1.61
    arser
    0.85
    algia
    0.79
    sov
    0.77
    unia
    0.74
    ernel
    0.74
    vers
    0.69
     Crusade
    0.68
     Affairs
    0.67
     Reloaded
    0.67
    Activations Density 0.013%

    No Known Activations