© 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. 11407
    Prev
    Next
    INDEX
    Explanations

    dates and events related to specific incidents or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    key moments and events related to significant dates or occurrences

    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
    Recommend
    -0.85
    catentry
    -0.84
     [+
    -0.80
    visor
    -0.73
     spam
    -0.72
     feedback
    -0.69
     enqu
    -0.68
     pc
    -0.66
    visors
    -0.66
     recommendation
    -0.65
    POSITIVE LOGITS
     roared
    1.07
     unfolded
    1.04
     awoke
    1.00
     crowned
    0.86
     awaits
    0.85
     etched
    0.84
     plunged
    0.84
     defied
    0.84
     vanquished
    0.83
     ushered
    0.83
    Activations Density 0.677%

    No Known Activations