© 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. 23507
    Prev
    Next
    INDEX
    Explanations

    phrases containing the phrase 'world-class'

    oai_token-act-pair · gpt-3.5-turbo

    references to "world-class" attributes or qualities

    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
     Ell
    -0.81
     Ital
    -0.80
     Carly
    -0.71
     Clyde
    -0.69
     beads
    -0.68
    ï¸ı
    -0.65
     torches
    -0.64
     Wong
    -0.63
    pload
    -0.62
     Cox
    -0.62
    POSITIVE LOGITS
    wide
    1.45
    level
    1.19
    Wide
    1.16
    based
    1.15
    issued
    1.10
    oriented
    1.08
    appointed
    1.06
    specific
    1.06
    sized
    1.06
    standard
    1.04
    Activations Density 0.113%

    No Known Activations