© 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. 24057
    Prev
    Next
    INDEX
    Explanations

    words related to the prefix "un-"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Un" related to various organizations or concepts

    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
    OPLE
    -0.76
     enhancement
    -0.66
     aquarium
    -0.62
     chase
    -0.61
     slamming
    -0.61
     CPC
    -0.61
     toss
    -0.61
     Tut
    -0.60
     mos
    -0.59
     shower
    -0.58
    POSITIVE LOGITS
    usual
    1.34
    finished
    1.22
    cles
    1.20
    sung
    1.20
    holy
    1.20
    itarian
    1.19
    surprisingly
    1.18
    official
    1.16
    itary
    1.16
    happy
    1.15
    Activations Density 0.017%

    No Known Activations