© 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. 2494
    Prev
    Next
    INDEX
    Explanations

    phrases related to emphasizing or highlighting specific information

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "some of."

    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
     preferably
    -0.65
    leep
    -0.61
     agre
    -0.60
     mathemat
    -0.60
    achy
    -0.58
    ciation
    -0.58
    aturdays
    -0.56
    ONS
    -0.56
    abis
    -0.56
     notwithstanding
    -0.56
    POSITIVE LOGITS
     these
    1.02
     those
    0.95
     the
    0.87
     our
    0.85
    these
    0.83
    those
    0.77
     its
    0.76
     them
    0.74
     my
    0.72
     their
    0.71
    Activations Density 0.107%

    No Known Activations