© 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. 8-RES-JB
    11. 520
    Prev
    Next
    INDEX
    Explanations

    links or locations within a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the availability or location of information or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tons
    -0.87
     boundaries
    -0.66
     typh
    -0.64
     correctness
    -0.64
     antidepressants
    -0.63
    uked
    -0.62
     judgment
    -0.62
     reven
    -0.61
     Trials
    -0.61
     vaccinations
    -0.59
    POSITIVE LOGITS
     HERE
    1.12
     here
    0.86
    hematically
    0.83
     elsewhere
    0.82
    uti
    0.81
     below
    0.78
    TAIN
    0.77
    ById
    0.75
    iasco
    0.73
     Below
    0.72
    Activations Density 0.071%

    No Known Activations