© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11284
    Prev
    Next
    INDEX
    Explanations

    expressions of opinion or personal judgment

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to speech and expression of thoughts

    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
    unal
    -0.63
    agascar
    -0.62
    pered
    -0.62
    aired
    -0.60
     Flavoring
    -0.59
    astern
    -0.58
    ockets
    -0.58
    actionDate
    -0.57
    agra
    -0.57
     recomm
    -0.56
    POSITIVE LOGITS
     '
    1.29
     '[
    1.28
     hey
    1.20
     "'
    1.19
     `
    1.14
     \"
    1.08
     '(
    1.07
     wow
    0.99
     "
    0.98
     hello
    0.97
    Activations Density 0.148%

    No Known Activations