© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 8596
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that summarize information or opinions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to summarization or encapsulating information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hair
    -0.84
    eworld
    -0.82
    ellen
    -0.74
    ali
    -0.73
    ship
    -0.69
    oos
    -0.67
    obs
    -0.67
    ally
    -0.65
     nose
    -0.65
    beer
    -0.65
    POSITIVE LOGITS
     summar
    1.39
     summed
    1.30
     summarize
    1.08
     summarizes
    1.04
     summarized
    1.03
    ãĤ©
    0.99
     succinct
    0.93
     encaps
    0.82
     sum
    0.81
     summ
    0.80
    Activations Density 0.014%

    No Known Activations