© 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. 4-RES-JB
    11. 22246
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to personal actions, especially in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    references to the subject "he" in various contexts

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

    No Comments

    Negative Logits
    earch
    -0.77
    arsity
    -0.69
    ormal
    -0.63
    berra
    -0.62
    ienne
    -0.62
    atlantic
    -0.62
    rame
    -0.61
    ãĥ©ãĥ³
    -0.61
    Prem
    -0.61
    ullivan
    -0.59
    POSITIVE LOGITS
    'll
    1.10
    'd
    1.08
    've
    0.94
     knew
    0.90
    're
    0.89
     didnt
    0.86
     drank
    0.85
     wandered
    0.84
     encount
    0.83
     wand
    0.83
    Activations Density 0.700%

    No Known Activations