© 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. 7751
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal relationships and associations

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals' advocacy and support for various social and political causes

    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
     tomorrow
    -0.72
    ?".
    -0.63
     Impossible
    -0.63
    ?).
    -0.63
     TOTAL
    -0.63
    ?!"
    -0.62
    ILLE
    -0.61
    ={
    -0.61
     unus
    -0.60
    ueless
    -0.59
    POSITIVE LOGITS
     throughout
    0.86
     despite
    0.82
    particularly
    0.79
     stemming
    0.76
    especially
    0.76
     insofar
    0.75
     since
    0.74
     whom
    0.73
     evidenced
    0.72
     especially
    0.71
    Activations Density 0.446%

    No Known Activations