© 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. 10-RES-JB
    11. 16264
    Prev
    Next
    INDEX
    Explanations

    phrases indicating lack of surprise or predictability

    oai_token-act-pair · gpt-3.5-turbo

    expressions of lack of surprise or inevitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bindings
    -0.62
    nect
    -0.59
    english
    -0.58
    JM
    -0.57
    incarn
    -0.57
     thru
    -0.56
    MpServer
    -0.56
     hone
    -0.55
    chers
    -0.55
     Amon
    -0.55
    POSITIVE LOGITS
     surprising
    1.21
     surprise
    1.19
     exaggeration
    1.02
     surpr
    0.97
     coincidence
    0.96
     unreasonable
    0.95
     fault
    0.88
     surprised
    0.88
     surprises
    0.83
    loss
    0.80
    Activations Density 0.209%

    No Known Activations