© 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. 18607
    Prev
    Next
    INDEX
    Explanations

    mentions of reasons or causes for various outcomes or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express conditions or issues associated with the concept of "a lack" or "a fear" in various contexts

    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
    tops
    -0.91
    accompan
    -0.79
    ographs
    -0.78
     Steps
    -0.73
    evidence
    -0.73
    ishers
    -0.73
    amines
    -0.70
     equivalents
    -0.69
    adult
    -0.67
    agues
    -0.66
    POSITIVE LOGITS
     misunderstanding
    1.47
     lack
    1.34
     combination
    1.25
     faulty
    1.14
     misconception
    1.13
     misinterpret
    1.11
     desire
    1.11
     typo
    1.09
     mistaken
    1.06
     mismatch
    1.05
    Activations Density 0.173%

    No Known Activations