© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 23271
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing precision or exactness

    oai_token-act-pair · gpt-3.5-turbo

    phrases that assert or emphasize something as being "exactly" the case

    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
     extensively
    -0.71
     greatly
    -0.67
     vigorously
    -0.67
     immensely
    -0.66
    strong
    -0.64
    ework
    -0.63
     enormously
    -0.62
    early
    -0.60
     widely
    -0.59
    ishly
    -0.59
    POSITIVE LOGITS
     opposite
    0.94
     what
    0.88
    what
    0.75
     why
    0.74
    assis
    0.72
     how
    0.69
    ãĤ¨
    0.68
     WHAT
    0.67
    ibaba
    0.67
     zero
    0.65
    Activations Density 0.032%

    No Known Activations