© 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. 3886
    Prev
    Next
    INDEX
    Explanations

    phrases related to positivity or benefit

    oai_token-act-pair · gpt-3.5-turbo

    connections between positive and negative effects in various contexts

    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
    eday
    -0.91
    yrights
    -0.82
    figured
    -0.78
    etimes
    -0.76
     Brist
    -0.76
    figure
    -0.75
     Travels
    -0.75
    ©¶æ¥µ
    -0.74
     Chapters
    -0.74
    ramids
    -0.72
    POSITIVE LOGITS
     negative
    2.21
     Negative
    2.00
    negative
    1.99
     positive
    1.97
     negativity
    1.93
     neutral
    1.86
    positive
    1.80
     Positive
    1.78
     negatives
    1.74
     unfavorable
    1.69
    Activations Density 0.162%

    No Known Activations