© 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. 10455
    Prev
    Next
    INDEX
    Explanations

    frequency-related data points like days of the week, months, or percentages

    oai_token-act-pair · gpt-3.5-turbo

    references to specific days and time periods in relation to events

    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
    ITNESS
    -0.65
     paternity
    -0.62
     Founding
    -0.62
     VIDEOS
    -0.61
     pedigree
    -0.58
    umbn
    -0.57
     curator
    -0.57
     Pats
    -0.54
     Lifetime
    -0.54
     Concepts
    -0.53
    POSITIVE LOGITS
     amid
    1.10
     owing
    0.97
     despite
    0.92
     due
    0.89
     thanks
    0.84
    due
    0.83
    despite
    0.81
     partly
    0.80
    thanks
    0.80
     exacerb
    0.77
    Activations Density 0.186%

    No Known Activations