© 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. 4-RES-JB
    11. 7245
    Prev
    Next
    INDEX
    Explanations

    instances where the term "second" is used in a specific context, often related to rankings or categorizations

    oai_token-act-pair · gpt-3.5-turbo

    references to "second" in various contexts, particularly in relation to classification or degree

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

    No Comments

    Negative Logits
    Paper
    -0.74
    roots
    -0.71
    Marginal
    -0.70
    IGHTS
    -0.67
    restling
    -0.67
    Cache
    -0.67
    ãĤĭ
    -0.67
     SPACE
    -0.66
    tics
    -0.65
     Simulator
    -0.65
    POSITIVE LOGITS
     baseman
    1.21
    arily
    1.10
    hand
    1.00
     consecutive
    0.84
     successive
    0.81
     cousin
    0.80
    aries
    0.80
     thirds
    0.80
    assian
    0.79
    nd
    0.78
    Activations Density 0.047%

    No Known Activations