© 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. 11580
    Prev
    Next
    INDEX
    Explanations

    phrases related to education or teaching

    oai_token-act-pair · gpt-3.5-turbo

    mentions of education and awareness

    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
    imposed
    -0.68
    Syn
    -0.65
    pload
    -0.63
     undone
    -0.63
    Pull
    -0.62
    ãĤ»
    -0.61
    ãĥĪ
    -0.60
    ãģ®å
    -0.60
     Vengeance
    -0.57
    76561
    -0.57
    POSITIVE LOGITS
     about
    0.97
    about
    0.88
     populace
    0.88
    selves
    0.86
     ignorant
    0.82
     minds
    0.81
     ABOUT
    0.80
     guesses
    0.80
    liter
    0.78
     educate
    0.78
    Activations Density 0.113%

    No Known Activations