© 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. 9-RES-JB
    11. 1861
    Prev
    Next
    INDEX
    Explanations

    first-person singular and second-person singular pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    first-person and second-person pronouns and their related verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     largeDownload
    -0.81
     discrep
    -0.79
    Offline
    -0.76
    Ë
    -0.65
    tons
    -0.64
     Vine
    -0.63
    holding
    -0.62
    eret
    -0.62
    <?
    -0.61
    ãĤ¤ãĥĪ
    -0.61
    POSITIVE LOGITS
     ever
    1.09
     even
    0.84
     succumb
    0.81
    atown
    0.80
     EVER
    0.79
     commence
    0.78
     embark
    0.77
     officially
    0.77
     begin
    0.74
     formally
    0.72
    Activations Density 0.135%

    No Known Activations