© 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. 10-RES-JB
    11. 6412
    Prev
    Next
    INDEX
    Explanations

    information related to organizations, funding, and establishment of various entities

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "with" indicating partnerships or collaborations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    deen
    -0.83
    here
    -0.82
    hops
    -0.70
    fuck
    -0.70
    ertain
    -0.69
    fair
    -0.69
    recy
    -0.68
    ounters
    -0.67
    sburg
    -0.66
    MORE
    -0.65
    POSITIVE LOGITS
     assistance
    1.25
     help
    1.18
     permission
    1.07
     intention
    1.04
     regard
    1.01
     contributions
    0.98
     intent
    0.97
     regards
    0.97
    stood
    0.96
     complicity
    0.94
    Activations Density 0.157%

    No Known Activations