© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4-RES-JB
    11. 3982
    Prev
    Next
    INDEX
    Explanations

    adjectives related to high quality or perfection

    oai_token-act-pair · gpt-3.5-turbo

    words related to excellence and high quality

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

    No Comments

    Negative Logits
    NetMessage
    -0.82
    channelAvailability
    -0.74
    addon
    -0.70
    gap
    -0.68
     Flavoring
    -0.66
     Franch
    -0.65
     accus
    -0.63
    ãĤ®
    -0.62
    azine
    -0.62
    udeb
    -0.62
    POSITIVE LOGITS
     impecc
    0.88
     meticulous
    0.76
     quality
    0.76
     exquisite
    0.75
    ulously
    0.73
     exceptional
    0.72
    buff
    0.72
     precision
    0.71
    cellence
    0.71
     preserved
    0.71
    Activations Density 0.043%

    No Known Activations