© 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. 17421
    Prev
    Next
    INDEX
    Explanations

    phrases related to the act of checking

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "checking"

    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
    si
    -0.89
    bra
    -0.79
    yon
    -0.75
    efer
    -0.75
    talk
    -0.71
    bal
    -0.67
    els
    -0.67
    sis
    -0.67
    mpeg
    -0.65
    cms
    -0.65
    POSITIVE LOGITS
    redients
    0.93
    allery
    0.82
    HAM
    0.82
     electron
    0.77
    GGGGGGGG
    0.76
     exha
    0.73
    tons
    0.72
     conduc
    0.71
    ansk
    0.69
    ADRA
    0.69
    Activations Density 0.143%

    No Known Activations