© 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. 9-RES-JB
    11. 18124
    Prev
    Next
    INDEX
    Explanations

    comparative words or phrases expressing a degree of something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong evaluation or intensity regarding topics or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     forever
    -0.76
     ALWAYS
    -0.75
     [/
    -0.73
    rish
    -0.71
     sickness
    -0.70
     wast
    -0.69
    "},"
    -0.69
     infinite
    -0.68
    âĻ¥
    -0.67
     thats
    -0.67
    POSITIVE LOGITS
     publicized
    1.04
     criticized
    1.02
     criticised
    0.98
     contentious
    0.96
     controvers
    0.95
    odox
    0.95
     controversial
    0.95
     scathing
    0.93
     hotly
    0.87
     diplomatic
    0.86
    Activations Density 0.425%

    No Known Activations