© 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. 2299
    Prev
    Next
    INDEX
    Explanations

    phrases related to general concepts or statements

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "something" in various contexts

    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
    stice
    -0.81
    ortex
    -0.78
    iday
    -0.76
    de
    -0.75
    Fight
    -0.72
    answer
    -0.71
    sie
    -0.71
    querade
    -0.70
    oise
    -0.69
    ename
    -0.69
    POSITIVE LOGITS
     else
    1.27
    Else
    1.02
     akin
    0.94
     we
    0.88
     unheard
    0.82
     you
    0.78
     Else
    0.77
     happening
    0.75
     everyone
    0.73
     nobody
    0.72
    Activations Density 0.046%

    No Known Activations