© 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. 15064
    Prev
    Next
    INDEX
    Explanations

    references to additional or supplementary information

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating ongoing political discourse and controversies

    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
    sie
    -0.75
    arial
    -0.71
    tera
    -0.70
    reen
    -0.66
    ãĥĥãĥĪ
    -0.65
    ãĤ©
    -0.61
    orescence
    -0.61
    Border
    -0.61
    idem
    -0.60
    MIT
    -0.60
    POSITIVE LOGITS
     VIDEOS
    0.97
    ONSORED
    0.91
    ĸļ
    0.81
    enegger
    0.80
    osponsors
    0.79
    EStream
    0.77
    ellen
    0.74
    bilt
    0.70
    20439
    0.66
     MORE
    0.65
    Activations Density 0.019%

    No Known Activations