© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10131
    Prev
    Next
    INDEX
    Explanations

    phrases expressing preference or positive sentiment towards various things

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express strong positive sentiments towards specific subjects or concepts

    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
    Loading
    -0.87
    ailable
    -0.80
    uthor
    -0.73
    ģĸ
    -0.72
     whence
    -0.72
    imester
    -0.71
    ħĭ
    -0.71
    udder
    -0.71
    Recommended
    -0.71
    Default
    -0.70
    POSITIVE LOGITS
     idea
    1.55
     simplicity
    1.23
     smell
    1.16
     vibe
    1.10
     notion
    1.09
     concept
    1.09
     feeling
    1.03
     fact
    1.02
     taste
    1.00
     way
    0.99
    Activations Density 0.195%

    No Known Activations