© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 18935
    Prev
    Next
    INDEX
    Explanations

    references to future plans or tasks

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to plans or planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OX
    -0.70
    20439
    -0.67
    Mit
    -0.64
    MY
    -0.62
    Clar
    -0.62
    GD
    -0.59
    Grade
    -0.59
    Reviewer
    -0.58
    Way
    -0.57
    ":{"
    -0.57
    POSITIVE LOGITS
     OPEC
    0.64
     Mub
    0.62
    ribute
    0.59
    aito
    0.58
     TBA
    0.57
     CONC
    0.57
     Shards
    0.57
    owship
    0.54
     Qi
    0.53
     indu
    0.52
    Activations Density 0.222%

    No Known Activations