© 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. 11139
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to something that triggers or initiates a particular action or event

    oai_token-act-pair · gpt-3.5-turbo

    terms related to causes of events or reasons behind actions

    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
    onyms
    -0.88
    rug
    -0.75
    erer
    -0.74
    opers
    -0.73
    omer
    -0.71
    basketball
    -0.71
    pper
    -0.69
    iciency
    -0.69
    pes
    -0.67
    atri
    -0.67
    POSITIVE LOGITS
    eous
    0.83
     groundwork
    0.76
     GOODMAN
    0.75
     impetus
    0.74
    姫
    0.72
     behind
    0.71
    ãĥ¼ãĥĨãĤ£
    0.71
     catalyst
    0.69
    ãĥ¼ãĥĨ
    0.66
     largeDownload
    0.66
    Activations Density 0.029%

    No Known Activations