© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 14149
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific type of spicy pepper, cayenne pepper

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to the cayenne pepper and its various usages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alien
    -0.80
    ONS
    -0.70
     DPR
    -0.69
    abase
    -0.69
    arent
    -0.68
     Stanton
    -0.65
    DM
    -0.65
    annis
    -0.63
     Spawn
    -0.63
    room
    -0.62
    POSITIVE LOGITS
    enne
    1.32
    sie
    0.98
    hoe
    0.89
    ño
    0.84
    pload
    0.81
    fer
    0.76
     pepper
    0.70
    ville
    0.70
    icho
    0.70
    wich
    0.70
    Activations Density 0.009%

    No Known Activations