© 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. 21646
    Prev
    Next
    INDEX
    Explanations

    phrases involving interactions or relationships with other individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to people and interpersonal relationships

    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
     Lans
    -0.65
     Canaver
    -0.65
     Petraeus
    -0.60
    olver
    -0.59
    ãĥ©ãĥ³
    -0.57
     exceptions
    -0.56
    outhern
    -0.56
    ãĤ¬
    -0.56
    oly
    -0.56
    inventoryQuantity
    -0.55
    POSITIVE LOGITS
    worldly
    1.50
     person
    1.11
     peoples
    0.98
     humans
    0.85
     persons
    0.84
     sentient
    0.83
     people
    0.83
    's
    0.82
     party
    0.81
     human
    0.81
    Activations Density 0.101%

    No Known Activations