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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 14769
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs indicating discourse or thought

    oai_token-act-pair · gpt-3.5-turbo

    first-person statements and expressions of personal opinion

    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
     Mile
    -0.61
     Monthly
    -0.60
     ILCS
    -0.58
     Uniform
    -0.58
     Afterwards
    -0.57
    Scroll
    -0.57
    Offline
    -0.57
     undisclosed
    -0.56
     Delicious
    -0.56
     unknown
    -0.56
    POSITIVE LOGITS
    Rather
    1.02
     merely
    1.02
    gemony
    1.01
     simply
    0.92
    Instead
    0.86
    issions
    0.85
    mere
    0.82
    sole
    0.81
     Rather
    0.81
    're
    0.79
    Activations Density 0.189%

    No Known Activations