© 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. 7436
    Prev
    Next
    INDEX
    Explanations

    terms related to weight or measurement, particularly involving large quantities

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "ton."

    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
     imagination
    -0.68
     RTX
    -0.66
     Belief
    -0.66
    代
    -0.64
     counselors
    -0.62
     Advice
    -0.61
    AAAAAAAA
    -0.61
     Antar
    -0.60
     forgiveness
    -0.59
    ï¸
    -0.58
    POSITIVE LOGITS
    neau
    1.10
    ysis
    0.99
    nel
    0.97
    nian
    0.94
    tery
    0.91
    odon
    0.90
    nia
    0.89
    ality
    0.88
    aler
    0.87
    alian
    0.86
    Activations Density 0.014%

    No Known Activations