© 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. 4-RES-JB
    11. 15284
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases that sum up information or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to summarization

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

    No Comments

    Negative Logits
    duct
    -0.69
    ansas
    -0.67
    ellen
    -0.66
    ali
    -0.66
    ship
    -0.66
    hair
    -0.64
    hips
    -0.63
    eland
    -0.63
    bies
    -0.62
    ships
    -0.61
    POSITIVE LOGITS
     summed
    0.99
     summar
    0.93
     succinct
    0.92
    ãĤ©
    0.82
    STAT
    0.80
     summarize
    0.79
    ãĤ¢ãĥ«
    0.78
    ãĤ¶
    0.75
     summarized
    0.74
     encaps
    0.72
    Activations Density 0.028%

    No Known Activations