© 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. 6-RES-JB
    11. 2913
    Prev
    Next
    INDEX
    Explanations

    words related to academic qualifications and formal titles

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to causality and fundamental status in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itars
    -0.77
    builders
    -0.69
    rooms
    -0.69
    urches
    -0.64
     Rooms
    -0.64
    urrencies
    -0.63
     Pets
    -0.62
    ouls
    -0.62
    nces
    -0.61
    eworks
    -0.61
    POSITIVE LOGITS
     standpoint
    0.86
     inhibitor
    0.75
     perspective
    0.74
     endorsement
    0.69
    elist
    0.67
     indicator
    0.66
    ussian
    0.65
     approximation
    0.65
     bucket
    0.64
     diploma
    0.64
    Activations Density 1.014%

    No Known Activations