© 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. 8-RES-JB
    11. 22689
    Prev
    Next
    INDEX
    Explanations

    adjectives describing high quality or excellence

    oai_token-act-pair · gpt-3.5-turbo

    terms related to artistic or creative expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStream
    -0.71
     Presumably
    -0.59
    wikipedia
    -0.58
    assium
    -0.58
    anamo
    -0.58
    _.
    -0.58
    agra
    -0.56
     anyway
    -0.56
     facto
    -0.56
    lyak
    -0.55
    POSITIVE LOGITS
     customizable
    0.86
     versatility
    0.86
     immersive
    0.84
     excellence
    0.79
     curated
    0.79
    ersive
    0.78
     unparalleled
    0.75
     diverse
    0.74
     personalized
    0.73
     versatile
    0.73
    Activations Density 0.886%

    No Known Activations