© 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. 20575
    Prev
    Next
    INDEX
    Explanations

    phrases related to going beyond limits or boundaries

    oai_token-act-pair · gpt-3.5-turbo

    prefixes and roots related to the concept of excess or overextension

    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
    nces
    -0.72
    trak
    -0.67
    PLA
    -0.66
    =/
    -0.61
    ulhu
    -0.60
    sym
    -0.60
    ny
    -0.58
    abouts
    -0.58
    letters
    -0.56
    CHAT
    -0.56
    POSITIVE LOGITS
    ealous
    1.05
    bitious
    0.87
    adows
    0.86
    whel
    0.86
    uled
    0.79
    ighed
    0.78
    arded
    0.76
    angs
    0.75
    aken
    0.74
    umped
    0.72
    Activations Density 0.028%

    No Known Activations