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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3-RES-JB
    6. 1723
    Prev
    Next
    INDEX
    Explanations

    keywords related to recreational activities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of recreation activities or facilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sudden
    -0.64
     infall
    -0.63
     monstrous
    -0.62
    individual
    -0.62
     maternal
    -0.61
    shape
    -0.61
    gran
    -0.61
    ker
    -0.61
    peror
    -0.61
    ylan
    -0.60
    POSITIVE LOGITS
     Recreation
    1.04
     Recre
    0.89
     recreation
    0.88
     Enhancement
    0.83
    nesota
    0.81
     Facilities
    0.77
    iage
    0.72
     Resort
    0.72
    ally
    0.72
    isure
    0.70
    Activations Density 0.011%

    No Known Activations