© 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. 20372
    Prev
    Next
    INDEX
    Explanations

    names with hyphens

    oai_token-act-pair · gpt-3.5-turbo

    proper names, particularly those of people

    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
     indic
    -0.68
     headlines
    -0.67
     clutch
    -0.65
     counties
    -0.65
     Republicans
    -0.65
     airports
    -0.64
     HT
    -0.64
     OC
    -0.63
     Slip
    -0.63
     Raider
    -0.63
    POSITIVE LOGITS
    Pierre
    1.59
    Cla
    1.58
    Louis
    1.48
    Marie
    1.44
    Fran
    1.44
    Paul
    1.39
    Marc
    1.39
    Luc
    1.38
    Philipp
    1.38
    Georg
    1.37
    Activations Density 0.035%

    No Known Activations