© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3453
    Prev
    Next
    INDEX
    Explanations

    references to technology, particularly the internet and the web

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the internet and media, particularly focusing on their implications and uses in society

    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
    edIn
    -0.74
    ĪĴ
    -0.71
    conserv
    -0.67
    ibi
    -0.63
    Capt
    -0.61
    ļé
    -0.61
    Grab
    -0.61
    pur
    -0.61
    ¶æ
    -0.60
     Gleaming
    -0.60
    POSITIVE LOGITS
    osphere
    1.13
     realm
    0.92
     itself
    0.89
     microbiome
    0.88
     era
    0.87
     ecosystem
    0.84
     economy
    0.83
     sphere
    0.82
    waves
    0.79
     continuum
    0.78
    Activations Density 0.352%

    No Known Activations