© 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. 0-RES-JB
    11. 6807
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with "on."

    oai_token-act-pair · gpt-3.5-turbo

    the preposition "on."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mathemat
    -0.82
    ibaba
    -0.71
    Ire
    -0.68
    HAHAHAHA
    -0.67
     cryst
    -0.67
    76561
    -0.67
     millenn
    -0.65
    HAHA
    -0.65
    CHQ
    -0.64
     skelet
    -0.62
    POSITIVE LOGITS
     on
    1.86
     upon
    1.23
     On
    1.19
     onto
    1.18
     ON
    1.12
     atop
    1.12
    On
    1.10
     aboard
    1.09
    on
    1.03
     onboard
    0.95
    Activations Density 0.379%

    No Known Activations