© 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. 2-RES-JB
    11. 17165
    Prev
    Next
    INDEX
    Explanations

    phrases related to extreme points or levels, such as highs and lows

    oai_token-act-pair · gpt-3.5-turbo

    terms related to highs and lows, particularly in contexts like finance or performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Fac
    -0.80
    Austral
    -0.73
    shapeshifter
    -0.73
    RECT
    -0.72
    OTS
    -0.72
    Stud
    -0.69
    Shell
    -0.69
    HOU
    -0.69
    Nation
    -0.69
    BUG
    -0.67
    POSITIVE LOGITS
     highs
    1.28
     lows
    1.18
    terness
    1.02
    terday
    0.94
    mith
    0.84
    poons
    0.79
     heights
    0.79
    creen
    0.76
    daq
    0.75
    itudes
    0.74
    Activations Density 0.012%

    No Known Activations