© 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. 7432
    Prev
    Next
    INDEX
    Explanations

    verbs related to receiving, creating, wearing, sending, facing, providing, gathering, taking, and making

    oai_token-act-pair · gpt-3.5-turbo

    past tense verbs and phrases related to actions taken or experienced

    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
     Quentin
    -0.74
     Metatron
    -0.72
     Barron
    -0.64
     Zeit
    -0.62
     stal
    -0.61
     IB
    -0.58
     Dmit
    -0.58
     Ballard
    -0.57
     Patri
    -0.57
     pend
    -0.56
    POSITIVE LOGITS
    abouts
    0.85
    ãĥ¼ãĤ¯
    0.78
    ãĤ´ãĥ³
    0.71
    lde
    0.67
    otype
    0.66
    igh
    0.66
    uggle
    0.63
    itud
    0.63
    ibaba
    0.61
     deems
    0.60
    Activations Density 0.730%

    No Known Activations