© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7063
    Prev
    Next
    INDEX
    Explanations

    phrases related to relationships and interpersonal interactions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "having an" and related expressions

    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
    arning
    -0.77
     Posts
    -0.75
    Features
    -0.72
    amazon
    -0.70
    ATURES
    -0.70
     Tens
    -0.67
     Countries
    -0.66
    Links
    -0.65
    interstitial
    -0.63
    Shipping
    -0.61
    POSITIVE LOGITS
     conversation
    1.18
     chance
    1.10
     conversations
    1.04
     meltdown
    1.04
    iphany
    0.98
     affair
    0.98
     discussion
    0.91
     blast
    0.89
     confrontation
    0.87
     flashback
    0.86
    Activations Density 0.214%

    No Known Activations