© 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. 11-RES-JB
    11. 23114
    Prev
    Next
    INDEX
    Explanations

    specific references to tests or testing procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to military or testing terminology related to aircraft or experiments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĤ
    -0.78
    Cro
    -0.74
    ãģ®å®
    -0.73
    gary
    -0.72
    iture
    -0.69
     traff
    -0.68
    wikipedia
    -0.67
     appropriated
    -0.66
    pedia
    -0.65
    joining
    -0.64
    POSITIVE LOGITS
     test
    2.48
     tests
    2.44
     testing
    2.30
     Test
    2.20
     Tests
    2.19
    Test
    2.16
     Testing
    2.15
     TEST
    2.15
    tests
    2.06
    test
    2.05
    Activations Density 0.295%

    No Known Activations