© 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. 2-RES-JB
    11. 12951
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly the name "Gregory."

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific name, "Gregory."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ker
    -0.92
    kers
    -0.87
    kHz
    -0.79
    jab
    -0.76
    consumer
    -0.76
    ipeg
    -0.75
    pper
    -0.73
    kick
    -0.72
    initialized
    -0.72
    href
    -0.71
    POSITIVE LOGITS
     Gregory
    1.07
     XVI
    0.83
     Angelo
    0.81
     GOODMAN
    0.79
    sburg
    0.78
    orius
    0.77
     Constantine
    0.73
     XIII
    0.72
     Balt
    0.72
     Peck
    0.72
    Activations Density 0.008%

    No Known Activations