© 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. 21265
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific luxury resort

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a resort

    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
    ector
    -0.74
    older
    -0.74
    hemat
    -0.70
    rod
    -0.69
    origin
    -0.67
    addy
    -0.66
    APH
    -0.65
    corn
    -0.63
    speed
    -0.62
    ERA
    -0.62
    POSITIVE LOGITS
     resort
    1.33
     resorts
    1.18
     Resort
    1.04
     resorted
    0.89
     therap
    0.87
     accommodation
    0.79
    igon
    0.76
     coerc
    0.76
     psychiat
    0.76
    ashtra
    0.74
    Activations Density 0.006%

    No Known Activations