© 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. 18684
    Prev
    Next
    INDEX
    Explanations

    expressions related to surprising or unusual events or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing surprise or confusion about unusual experiences or situations

    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
    vernment
    -0.64
    é¾į
    -0.59
    inoa
    -0.55
    azines
    -0.55
    illard
    -0.54
    ieri
    -0.54
    DATA
    -0.54
    WOOD
    -0.53
    olls
    -0.53
    NetMessage
    -0.52
    POSITIVE LOGITS
     like
    2.03
     LIKE
    1.67
    like
    1.39
     such
    1.35
     Like
    1.32
    Like
    1.22
    such
    1.08
     resembling
    0.91
     similar
    0.89
     akin
    0.86
    Activations Density 0.672%

    No Known Activations