© 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. 18696
    Prev
    Next
    INDEX
    Explanations

    websites or online platforms

    oai_token-act-pair · gpt-3.5-turbo

    relationships and mentions specifically tied to Twitch and its content

    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
     skim
    -0.66
    elson
    -0.64
    ã
    -0.64
    ument
    -0.62
    zsche
    -0.62
    asca
    -0.61
    reau
    -0.60
     wheelchair
    -0.60
     fetch
    -0.60
     canv
    -0.59
    POSITIVE LOGITS
    fing
    0.69
    Mini
    0.66
    vity
    0.64
    eways
    0.62
    Previous
    0.60
    CHAT
    0.59
    alker
    0.59
    urrencies
    0.58
     Advis
    0.58
    opers
    0.56
    Activations Density 0.291%

    No Known Activations