© 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. 4-RES-JB
    11. 22272
    Prev
    Next
    INDEX
    Explanations

    adjectives describing extreme intensity or severity

    oai_token-act-pair · gpt-3.5-turbo

    intensifiers or descriptors that convey a sense of severity or extremity

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

    No Comments

    Negative Logits
    CHAT
    -0.77
    INS
    -0.67
    brook
    -0.65
    LAN
    -0.65
    ACA
    -0.64
    ADS
    -0.62
    Stars
    -0.62
    Hub
    -0.62
     Glover
    -0.61
    EP
    -0.60
    POSITIVE LOGITS
     than
    1.66
    than
    1.38
     Than
    1.21
    oldemort
    0.76
     sounding
    0.76
     installments
    0.74
    erous
    0.74
     versions
    0.71
    iable
    0.70
    iated
    0.70
    Activations Density 0.162%

    No Known Activations