© 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. 18498
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of glamour or glamorized activities

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with glamour and extravagance

    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
    ansom
    -0.65
    ness
    -0.62
     Poles
    -0.62
     neutrality
    -0.61
     Alban
    -0.60
    VO
    -0.59
     silence
    -0.59
     tongue
    -0.59
     Africans
    -0.59
     reservoir
    -0.57
    POSITIVE LOGITS
    ures
    1.23
    ured
    1.11
    uring
    1.08
    urous
    1.02
    rast
    0.99
    urable
    0.99
    urus
    0.98
    itious
    0.97
    URES
    0.97
    ible
    0.96
    Activations Density 0.095%

    No Known Activations