© 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. 7-RES-JB
    11. 150
    Prev
    Next
    INDEX
    Explanations

    terms related to events, conferences, conventions, concerts, and competitions

    oai_token-act-pair · gpt-3.5-turbo

    references to events and gatherings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     overpowered
    -0.85
    eland
    -0.85
     phosphorus
    -0.77
    thy
    -0.75
    azy
    -0.73
    eness
    -0.73
    ppe
    -0.72
    zman
    -0.71
    ragon
    -0.71
    obile
    -0.71
    POSITIVE LOGITS
     invitations
    1.12
     exhibitions
    1.03
     conferences
    0.97
     seminars
    0.96
     meetings
    0.95
     dinners
    0.94
     competitions
    0.93
     fundra
    0.93
     presentations
    0.92
     tours
    0.92
    Activations Density 0.465%

    No Known Activations