© 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. 3-RES-JB
    11. 2798
    Prev
    Next
    INDEX
    Explanations

    descriptors related to hobbies

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hobbies and hobbyists

    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
    oti
    -0.66
     Samson
    -0.64
     Dign
    -0.64
    使
    -0.63
     skulls
    -0.63
     sclerosis
    -0.62
    utical
    -0.62
     curv
    -0.62
    天
    -0.62
    ×Ļ×
    -0.62
    POSITIVE LOGITS
     hobby
    1.27
    sonian
    0.91
    finder
    0.85
    reprene
    0.84
    ist
    0.84
    puter
    0.82
     fixme
    0.81
     actionGroup
    0.80
    bench
    0.80
     hobbies
    0.79
    Activations Density 0.009%

    No Known Activations