© 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. 6269
    Prev
    Next
    INDEX
    Explanations

    personal introductions and declarations of identity

    oai_token-act-pair · gpt-3.5-turbo

    phrases that introduce personal names and descriptors

    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
    externalActionCode
    -0.73
     stadiums
    -0.71
     caste
    -0.70
    ramid
    -0.68
    empt
    -0.67
     funer
    -0.67
    profit
    -0.67
     Marketable
    -0.67
     arenas
    -0.67
     airplanes
    -0.66
    POSITIVE LOGITS
     Gabriel
    1.27
     Markus
    1.27
     Chris
    1.26
     Richard
    1.24
     Daniel
    1.23
     Jonathan
    1.23
     Josh
    1.22
     Kevin
    1.22
     Geoffrey
    1.22
     Geoff
    1.22
    Activations Density 0.865%

    No Known Activations