© 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. 12264
    Prev
    Next
    INDEX
    Explanations

    metadata or editing features such as sections and edits in a document

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Edit" and related editing commands

    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
    gart
    -0.94
    milo
    -0.85
    uay
    -0.78
    IRD
    -0.77
    ciating
    -0.74
    esville
    -0.69
    cock
    -0.68
    ueller
    -0.67
    cosystem
    -0.67
    ynt
    -0.66
    POSITIVE LOGITS
     edit
    0.89
    edit
    0.85
     Edit
    0.76
     edits
    0.75
     summ
    0.68
    Edit
    0.68
    âĶĢâĶĢ
    0.65
    iton
    0.64
     editing
    0.64
     Vote
    0.63
    Activations Density 0.007%

    No Known Activations