© 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. 7909
    Prev
    Next
    INDEX
    Explanations

    phrases related to project updates or progress reports

    oai_token-act-pair · gpt-3.5-turbo

    the word "our" indicating collective experience or belonging

    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
    conom
    -0.78
    puff
    -0.75
    cum
    -0.72
    ppings
    -0.72
    bender
    -0.72
    ussen
    -0.70
    icter
    -0.69
     appears
    -0.69
    tar
    -0.69
    more
    -0.68
    POSITIVE LOGITS
    selves
    1.20
     own
    1.05
     beloved
    0.93
     motto
    0.87
     ourselves
    0.87
     collective
    0.86
     respective
    0.86
     ancestors
    0.85
     adversaries
    0.83
     dear
    0.83
    Activations Density 0.135%

    No Known Activations