© 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. 9982
    Prev
    Next
    INDEX
    Explanations

    person names, predominantly surnames

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, specifically names and titles

    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
    GROUND
    -0.65
    MODE
    -0.61
    Panel
    -0.60
    Assembly
    -0.60
    said
    -0.59
    PN
    -0.59
    lishes
    -0.58
     Pis
    -0.58
     provisional
    -0.57
    Methods
    -0.55
    POSITIVE LOGITS
     Jr
    1.23
    's
    1.07
     himself
    1.03
     Himself
    1.02
     aka
    1.00
    enegger
    0.99
     Sr
    0.97
     Syndrome
    0.88
     circa
    0.87
    itsch
    0.87
    Activations Density 0.303%

    No Known Activations