© 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. 22557
    Prev
    Next
    INDEX
    Explanations

    instances where something is described as having more or less of a particular quality or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing the concept of "more of" something

    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
    alez
    -0.65
    ynes
    -0.64
    yrs
    -0.62
    zai
    -0.62
    overe
    -0.62
    TOP
    -0.59
     livest
    -0.59
     withd
    -0.59
    months
    -0.57
    uden
    -0.56
    POSITIVE LOGITS
     course
    0.86
    course
    0.85
     an
    0.85
    erous
    0.85
     them
    0.80
     a
    0.76
     what
    0.74
     ourselves
    0.73
     us
    0.72
     those
    0.72
    Activations Density 0.075%

    No Known Activations