© 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. 10-RES-JB
    11. 16955
    Prev
    Next
    INDEX
    Explanations

    ideas and concepts mentioned in a document or conversation

    oai_token-act-pair · gpt-3.5-turbo

    the concept of significant ideas or proposals related to innovation or change

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Recording
    -0.87
    Record
    -0.77
    record
    -0.76
    gd
    -0.74
     Coverage
    -0.71
     Medals
    -0.71
    asters
    -0.70
     Record
    -0.70
     penalties
    -0.67
     Records
    -0.67
    POSITIVE LOGITS
     floated
    1.22
     hatched
    1.10
     tantal
    0.97
     intriguing
    0.96
     utopian
    0.93
     laughable
    0.93
     entertained
    0.93
     dreamed
    0.93
     plausible
    0.92
     appealing
    0.91
    Activations Density 0.261%

    No Known Activations