© 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. 11-RES-JB
    11. 1272
    Prev
    Next
    INDEX
    Explanations

    terms related to emotional reactions or personal sentiments

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to expressions of fear or dread

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arter
    -0.80
    uments
    -0.79
    arten
    -0.71
    sburg
    -0.68
    jong
    -0.67
    sburgh
    -0.67
     Edited
    -0.67
    ument
    -0.64
    fman
    -0.63
    FIELD
    -0.63
    POSITIVE LOGITS
     prospect
    1.60
     fact
    1.39
     idea
    1.34
     notion
    1.31
     possibility
    1.29
     sight
    1.28
     enorm
    1.27
     sudden
    1.25
     realization
    1.22
     suggestion
    1.21
    Activations Density 0.251%

    No Known Activations