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

    Neuronpedia

    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. 9-RES-JB
    11. 7364
    Prev
    Next
    INDEX
    Explanations

    information related to event details such as dates, locations, and participants

    oai_token-act-pair · gpt-3.5-turbo

    locations, events, and dates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    20439
    -0.83
     prey
    -0.81
    ccording
    -0.79
    phabet
    -0.78
    utsche
    -0.76
    ²¾
    -0.72
    utan
    -0.72
    earchers
    -0.72
     contend
    -0.71
     botched
    -0.71
    POSITIVE LOGITS
     Auditor
    1.23
     Marriott
    1.19
     Plaza
    1.19
     Pavilion
    1.17
     Hotel
    1.07
     Theatre
    1.06
     Downtown
    1.06
     Campus
    1.05
     Hilton
    1.04
     Stadium
    1.04
    Activations Density 0.343%

    No Known Activations