© 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. 10255
    Prev
    Next
    INDEX
    Explanations

    statements in which someone is expressing their awareness or lack of awareness

    oai_token-act-pair · gpt-3.5-turbo

    the verb "was" and its context in sentences

    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
    ãĥ¯
    -0.66
    Appearances
    -0.66
    llular
    -0.62
     Topics
    -0.62
     Invention
    -0.58
    ibi
    -0.56
     Rankings
    -0.56
    udeau
    -0.55
    igslist
    -0.55
     âĸº
    -0.55
    POSITIVE LOGITS
     unaware
    1.27
     glad
    1.23
     unsure
    1.20
     disappointed
    1.17
     pleased
    1.17
     saddened
    1.16
     aware
    1.15
     surprised
    1.14
     sorry
    1.14
     grateful
    1.12
    Activations Density 0.140%

    No Known Activations