© 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. 8-RES-JB
    11. 4567
    Prev
    Next
    INDEX
    Explanations

    references to the word "United"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "United."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prus
    -0.72
    MY
    -0.69
    CHR
    -0.66
    bard
    -0.66
    ouf
    -0.66
    ebook
    -0.66
    ï¸ı
    -0.64
    EGIN
    -0.63
    book
    -0.63
    eware
    -0.63
    POSITIVE LOGITS
     Nations
    1.08
     States
    1.08
     Methodist
    1.06
     Airlines
    1.00
     STATES
    0.95
    States
    0.89
    Health
    0.84
     Artists
    0.80
    sburg
    0.78
     Launch
    0.77
    Activations Density 0.030%

    No Known Activations