© 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. 19326
    Prev
    Next
    INDEX
    Explanations

    keywords related to stages or settings for events

    oai_token-act-pair · gpt-3.5-turbo

    references to a "stage" or settings where activities, performances, or events occur

    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
    vironment
    -0.74
     Uz
    -0.63
    ufact
    -0.63
    umar
    -0.62
     Bears
    -0.59
    uala
    -0.58
     Leaf
    -0.58
    ãģĦ
    -0.57
    arus
    -0.56
    istani
    -0.56
    POSITIVE LOGITS
    hands
    0.98
    craft
    0.87
    agne
    0.81
    yard
    0.77
     fright
    0.76
    aux
    0.74
    room
    0.72
     banter
    0.72
    co
    0.71
    stage
    0.71
    Activations Density 0.033%

    No Known Activations