© 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. 8-RES-JB
    11. 20461
    Prev
    Next
    INDEX
    Explanations

    sentences that end with a period and are likely critical or negative in tone

    oai_token-act-pair · gpt-3.5-turbo

    sentences expressing strong opinions or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     unsus
    -0.82
    escription
    -0.76
     earthqu
    -0.76
     cellar
    -0.74
    isbury
    -0.74
     belly
    -0.74
     basket
    -0.73
     carbohyd
    -0.73
     unseen
    -0.73
     inactive
    -0.72
    POSITIVE LOGITS
     Especially
    1.66
     Surely
    1.46
     Anyway
    1.44
     Particularly
    1.33
     Moreover
    1.31
     Wouldn
    1.31
     Nonetheless
    1.27
     Certainly
    1.26
     Furthermore
    1.25
     Thankfully
    1.25
    Activations Density 0.519%

    No Known Activations