© 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. 20600
    Prev
    Next
    INDEX
    Explanations

    text related to the composition or classification of elements, minerals, or resources

    oai_token-act-pair · gpt-3.5-turbo

    references to numbers and counts related to various categories or elements

    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
     nuns
    -0.72
     devs
    -0.71
     hikers
    -0.67
     lesbians
    -0.67
     vets
    -0.64
     guys
    -0.64
     hackers
    -0.64
     monks
    -0.64
     fishermen
    -0.63
     Italians
    -0.63
    POSITIVE LOGITS
     Selected
    0.83
    ®
    0.74
     recognized
    0.73
     predetermined
    0.71
     Recommended
    0.70
     Comprehensive
    0.70
     ®
    0.70
     Common
    0.70
    ®,
    0.70
    ordinary
    0.70
    Activations Density 0.453%

    No Known Activations