© 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. 1022
    Prev
    Next
    INDEX
    Explanations

    phrases expressing positive sentiment, feedback, or reactions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positive feedback or responses

    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
     someday
    -0.79
    sylvania
    -0.68
    tymology
    -0.67
     Tycoon
    -0.67
    owe
    -0.66
     Definition
    -0.65
    eday
    -0.65
    adium
    -0.64
    pta
    -0.64
     lest
    -0.64
    POSITIVE LOGITS
     disappointing
    1.38
    cellent
    1.37
     impressive
    1.32
     pleasant
    1.31
     lackluster
    1.29
     satisfactory
    1.23
     enjoyable
    1.22
     pleasantly
    1.20
    whelming
    1.18
     flawless
    1.16
    Activations Density 0.345%

    No Known Activations