© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 1999
    Prev
    Next
    INDEX
    Explanations

    first-person singular verbs

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and phrases indicating personal actions or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GI
    -0.62
     Needless
    -0.61
     Brus
    -0.60
    ouses
    -0.58
    shock
    -0.54
    RNA
    -0.54
    gem
    -0.54
     favourable
    -0.54
    Es
    -0.53
     Areas
    -0.53
    POSITIVE LOGITS
     fuckin
    0.95
     rul
    0.72
     lawy
    0.71
     uh
    0.71
     gonna
    0.70
     anyway
    0.68
    ...?
    0.67
    agall
    0.67
     contrace
    0.67
     alright
    0.67
    Activations Density 0.705%

    No Known Activations