© 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. 0-RES-JB
    11. 1228
    Prev
    Next
    INDEX
    Explanations

    the name "Jay" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Jay"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contamin
    -0.71
     assemblies
    -0.71
     wrapper
    -0.70
    helm
    -0.68
    ktop
    -0.68
    ãĥ¯
    -0.68
    elf
    -0.67
    ãĥĺ
    -0.67
     fa
    -0.66
    gob
    -0.62
    POSITIVE LOGITS
     Jay
    3.63
    Jay
    3.01
    jay
    1.79
     Jays
    1.53
     Kay
    1.34
     Ray
    1.26
     Jas
    1.23
     Josh
    1.23
    Bey
    1.23
     Sonny
    1.18
    Activations Density 0.017%

    No Known Activations