© 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. 8-RES-JB
    11. 22311
    Prev
    Next
    INDEX
    Explanations

    phrases related to location or positioning

    oai_token-act-pair · gpt-3.5-turbo

    words related to placards or placemaking

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sachs
    -0.65
    NESS
    -0.63
     Angus
    -0.62
     Realms
    -0.62
    ILY
    -0.60
    NEWS
    -0.59
     HRC
    -0.59
     jurisdiction
    -0.59
    SOURCE
    -0.59
     realism
    -0.59
    POSITIVE LOGITS
    ements
    1.32
    ental
    1.19
    ename
    1.15
    ating
    1.10
    ational
    1.06
    atron
    0.99
    atin
    0.99
    ate
    0.97
    atable
    0.97
    ently
    0.96
    Activations Density 0.032%

    No Known Activations