© 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. 11-RES-JB
    11. 17445
    Prev
    Next
    INDEX
    Explanations

    information related to news and accidents involving a specific location

    oai_token-act-pair · gpt-3.5-turbo

    segments that indicate updates or announcements related to various topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aukee
    -0.74
     veter
    -0.74
     oun
    -0.68
     awakening
    -0.66
    aturdays
    -0.65
     submar
    -0.64
     princ
    -0.63
     surplus
    -0.62
     Auditor
    -0.62
     grandson
    -0.61
    POSITIVE LOGITS
    Images
    1.26
    SOURCE
    1.20
    Featured
    1.15
    Thumbnail
    1.14
    Source
    1.11
    Via
    1.09
    via
    1.06
    Hat
    1.04
    advertising
    1.03
    Header
    0.96
    Activations Density 0.248%

    No Known Activations