© 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. 9-RES-JB
    11. 7414
    Prev
    Next
    INDEX
    Explanations

    the word "having" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "having" related to experiences or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reserv
    -0.67
     Posts
    -0.66
    aware
    -0.61
     anticipating
    -0.60
     serving
    -0.59
     Tradable
    -0.58
     premise
    -0.58
     gearing
    -0.58
    ilings
    -0.58
     heading
    -0.57
    POSITIVE LOGITS
     trouble
    1.16
     fun
    1.07
     difficulty
    0.90
     nightmares
    0.90
     intercourse
    0.88
     conversations
    0.88
     affairs
    0.88
     dinner
    0.86
     adventures
    0.85
     discussions
    0.83
    Activations Density 0.106%

    No Known Activations