© 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. 10-RES-JB
    11. 13655
    Prev
    Next
    INDEX
    Explanations

    proper names and initials, specifically looking for the letter "T"

    oai_token-act-pair · gpt-3.5-turbo

    names of people or characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.64
    HM
    -0.64
    HAEL
    -0.64
    phia
    -0.63
     bases
    -0.60
    agall
    -0.59
    ornia
    -0.59
    士
    -0.57
    WER
    -0.56
    æ©Ł
    -0.55
    POSITIVE LOGITS
    quart
    0.64
    jad
    0.63
     Jav
    0.63
    RPG
    0.59
    ãĥ¼ãĥ
    0.58
    aks
    0.57
    illance
    0.57
    ãĥŃ
    0.56
    allah
    0.56
    ãĤ¿
    0.55
    Activations Density 0.213%

    No Known Activations