© 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. 23895
    Prev
    Next
    INDEX
    Explanations

    phrases related to potential actions or outcomes

    oai_token-act-pair · gpt-3.5-turbo

    emphasized expressions that convey danger or risk

    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
     dispers
    -0.66
     Mous
    -0.66
     director
    -0.66
     Cameroon
    -0.64
     Mayo
    -0.64
     contraception
    -0.62
     Danish
    -0.62
     DNA
    -0.62
     leading
    -0.61
     Chev
    -0.61
    POSITIVE LOGITS
    »
    1.67
    ¹
    1.65
    į
    1.62
    ª
    1.59
    ¤
    1.54
    ¡
    1.51
    Ŀ
    1.50
    ®
    1.50
    ´
    1.49
    Ń
    1.48
    Activations Density 0.121%

    No Known Activations