© 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. 20657
    Prev
    Next
    INDEX
    Explanations

    words related to comfort and relaxation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and periods in the text

    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
     inform
    -0.84
     inhibit
    -0.81
     disadvantage
    -0.80
     inaccur
    -0.79
     policymakers
    -0.78
     correspond
    -0.75
     administrators
    -0.75
     enrol
    -0.74
    encing
    -0.74
     carbohyd
    -0.73
    POSITIVE LOGITS
     Been
    1.47
     Lots
    1.45
     Sounds
    1.40
     Definitely
    1.40
     Didn
    1.38
     Seems
    1.38
     Possibly
    1.38
     Makes
    1.36
     Looks
    1.35
     Totally
    1.34
    Activations Density 0.326%

    No Known Activations