© 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. 13698
    Prev
    Next
    INDEX
    Explanations

    emotions and subjective experiences

    oai_token-act-pair · gpt-3.5-turbo

    expressions of observation or commentary

    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
     sanctuary
    -0.70
     kit
    -0.67
     AA
    -0.65
     AAA
    -0.65
     BMC
    -0.64
     HS
    -0.63
     shield
    -0.63
     board
    -0.62
     barrier
    -0.62
     ALS
    -0.62
    POSITIVE LOGITS
    ifully
    1.43
    rarily
    1.30
    identally
    1.21
    orically
    1.21
    prisingly
    1.19
    hematically
    1.18
    xtap
    1.18
    itionally
    1.16
    rary
    1.15
    ately
    1.15
    Activations Density 0.223%

    No Known Activations