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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1-RES-JB
    11. 20157
    Prev
    Next
    INDEX
    Explanations

    phrases related to enthusiasts, especially in specific contexts like technology, sports, and hobbies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to enthusiasts across various fields or activities

    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
    OUT
    -0.70
    LS
    -0.67
     Dalai
    -0.64
    Kar
    -0.63
    transform
    -0.61
     Shattered
    -0.60
     Tol
    -0.60
     Kund
    -0.59
    Strength
    -0.58
     Dome
    -0.58
    POSITIVE LOGITS
     enthusiasts
    1.16
     enthusiast
    1.04
     hobby
    0.99
    icion
    0.89
    ateurs
    0.87
    userc
    0.80
    ateur
    0.77
    conservancy
    0.76
     racer
    0.75
     buffs
    0.75
    Activations Density 0.009%

    No Known Activations