© 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. 3920
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative expressions indicating degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    adverbs and phrases that express levels of intensity or comparison

    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
    ulence
    -0.78
    tesy
    -0.75
     VIDEOS
    -0.73
    iversary
    -0.69
     Landing
    -0.69
     Borders
    -0.69
     Lines
    -0.67
     absurdity
    -0.67
    çķ
    -0.65
    any
    -0.65
    POSITIVE LOGITS
     aware
    1.42
     interested
    1.40
     afraid
    1.34
     pleased
    1.33
     obsessed
    1.31
     allergic
    1.29
     proud
    1.28
     confident
    1.28
     concerned
    1.27
     inclined
    1.27
    Activations Density 0.258%

    No Known Activations