Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 16307
    Prev
    Next
    INDEX
    Explanations

    mentions of guided tours

    oai_token-act-pair · gpt-3.5-turbo

    references to guided activities and food services

    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
     piece
    -0.92
     result
    -0.85
     statement
    -0.83
     mistake
    -0.82
     situation
    -0.82
     thread
    -0.81
     segment
    -0.80
     mechanism
    -0.79
     barrier
    -0.79
     bunch
    -0.79
    POSITIVE LOGITS
     tours
    2.10
     dishes
    1.85
     meals
    1.78
     trips
    1.78
     visits
    1.77
     journeys
    1.72
     surveys
    1.62
     plots
    1.60
     lectures
    1.60
     outings
    1.59
    Activations Density 0.068%

    No Known Activations