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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 14470
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives expressing a high degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    adverbs indicating the degree or intensity of an action or condition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     IMAGES
    -0.72
    ggles
    -0.72
     VIDEOS
    -0.69
    ULE
    -0.67
    glers
    -0.65
    regate
    -0.65
     Awakens
    -0.64
    each
    -0.64
    yip
    -0.63
     Cause
    -0.63
    POSITIVE LOGITS
     reliant
    0.99
     dependent
    0.95
     involved
    0.90
     liable
    0.90
     aware
    0.89
     effected
    0.89
     affected
    0.89
     concerned
    0.88
     situated
    0.88
     confined
    0.88
    Activations Density 0.269%

    No Known Activations