© 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. 7-RES-JB
    11. 18059
    Prev
    Next
    INDEX
    Explanations

    words related to pushing boundaries, limits, and envelopes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to pushing boundaries or limits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SEA
    -0.76
    nces
    -0.73
     Laksh
    -0.69
    ×Ļ×
    -0.68
    FORE
    -0.68
    spring
    -0.67
    cise
    -0.66
    ÄŁ
    -0.65
    ]}
    -0.64
    /-
    -0.63
    POSITIVE LOGITS
     boundaries
    1.10
     envelope
    1.00
     agendas
    0.88
     buttons
    0.86
     harder
    0.84
     agenda
    0.84
     wedge
    0.79
     forward
    0.79
     onward
    0.77
     forwards
    0.76
    Activations Density 0.173%

    No Known Activations