© 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. 6446
    Prev
    Next
    INDEX
    Explanations

    phrases related to institutions or establishments

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the definite article "the."

    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
    adata
    -0.74
    hips
    -0.72
    ilde
    -0.70
     goodbye
    -0.66
    Downloadha
    -0.66
    illion
    -0.65
    tackle
    -0.64
    abel
    -0.64
    ATURES
    -0.64
    lock
    -0.63
    POSITIVE LOGITS
     same
    0.96
     latter
    0.95
     Philippines
    0.90
     Ancients
    0.89
     highest
    0.86
     Americas
    0.86
     utmost
    0.83
     aforementioned
    0.83
     Confederacy
    0.81
     poorest
    0.80
    Activations Density 0.212%

    No Known Activations