© 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. 23704
    Prev
    Next
    INDEX
    Explanations

    references to specific locations

    oai_token-act-pair · gpt-3.5-turbo

    elements related to geographical locations and activities

    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
    •contextual features
    unclear what it's firing on but feels like a 3-token feature

    No Comments

    Negative Logits
     accordingly
    -0.80
     [*
    -0.74
     furthermore
    -0.72
     Seym
    -0.71
    Footnote
    -0.70
    atever
    -0.70
     Vaugh
    -0.66
    DAQ
    -0.66
     disadvant
    -0.66
     anecd
    -0.65
    POSITIVE LOGITS
     nutshell
    0.70
     breast
    0.52
    erville
    0.52
    league
    0.51
     galaxy
    0.51
     Dead
    0.51
     Built
    0.50
    moon
    0.50
     Farming
    0.50
     cage
    0.49
    Activations Density 0.961%

    No Known Activations