© 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. 8-RES-JB
    11. 6241
    Prev
    Next
    INDEX
    Explanations

    phrases describing uniqueness or special characteristics of something

    oai_token-act-pair · gpt-3.5-turbo

    statements that highlight unique characteristics or advantages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Concern
    -0.75
     Hoy
    -0.69
     Worse
    -0.67
    ij士
    -0.65
     Tomorrow
    -0.63
    tty
    -0.63
    ãĤ§
    -0.62
    ilet
    -0.61
    olor
    -0.61
     behalf
    -0.60
    POSITIVE LOGITS
     seamlessly
    0.93
     simplicity
    0.87
     avoids
    0.82
     unlike
    0.80
     effortlessly
    0.80
     streamlined
    0.78
     uncond
    0.77
     comprehens
    0.77
     allows
    0.75
     esche
    0.74
    Activations Density 0.505%

    No Known Activations