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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 2862
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a measurement or degree of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the extent or degree of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    miah
    -0.69
    aldi
    -0.67
    ker
    -0.67
    verbs
    -0.64
     messenger
    -0.63
    leader
    -0.63
    swick
    -0.60
     tidy
    -0.58
    imer
    -0.58
    pton
    -0.57
    POSITIVE LOGITS
     extent
    1.01
     thereof
    0.87
    SPONSORED
    0.86
    lessness
    0.81
     amounts
    0.77
     practicable
    0.76
     of
    0.73
     variance
    0.73
     understatement
    0.72
     fault
    0.71
    Activations Density 0.028%

    No Known Activations