© 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. 7-RES-JB
    11. 21677
    Prev
    Next
    INDEX
    Explanations

    instructions related to cooking or arranging items in specific positions

    oai_token-act-pair · gpt-3.5-turbo

    instructions or guidelines related to physical tasks or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    akings
    -0.80
     Monthly
    -0.75
     Soup
    -0.73
     Reloaded
    -0.72
    QL
    -0.68
    MQ
    -0.68
     Codes
    -0.68
    Daily
    -0.68
     Trouble
    -0.67
    Tea
    -0.67
    POSITIVE LOGITS
     perpendicular
    1.32
     angled
    1.21
     horizontal
    1.06
     angle
    1.05
     vertically
    1.04
     downwards
    1.04
     vertical
    1.04
     perpend
    1.03
     angles
    1.02
     curved
    1.01
    Activations Density 0.835%

    No Known Activations