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

    Neuronpedia

    Jacobian LensNEW
    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. 0-RES-JB
    11. 12779
    Prev
    Next
    INDEX
    Explanations

    words related to physical discomfort or irritation

    oai_token-act-pair · gpt-3.5-turbo

    words related to "itch" or related discomfort

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     custod
    -0.67
     protected
    -0.66
     Nug
    -0.65
     orders
    -0.64
     power
    -0.64
     certificates
    -0.61
     certificate
    -0.61
     packets
    -0.60
     powers
    -0.60
     authenticated
    -0.59
    POSITIVE LOGITS
    itch
    4.60
    itches
    2.68
    ITCH
    2.64
    itching
    2.26
    itched
    1.97
    itcher
    1.87
    tch
    1.16
    atch
    1.15
    itsch
    1.12
    ich
    1.10
    Activations Density 0.006%

    No Known Activations