© 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. 16132
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with 'guest' and 'member' distinctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to guest status and membership

    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
     exting
    -0.74
     eleph
    -0.73
     scapego
    -0.71
     pione
    -0.67
    yg
    -0.67
     dispers
    -0.65
     franc
    -0.61
     snapshots
    -0.60
     territ
    -0.60
    Þ
    -0.60
    POSITIVE LOGITS
    Never
    1.02
    Guest
    0.77
    views
    0.74
    Activity
    0.72
    Uncommon
    0.72
    Not
    0.70
    ilded
    0.69
     Flavoring
    0.68
    mL
    0.66
    rawdownloadcloneembedreportprint
    0.65
    Activations Density 0.035%

    No Known Activations