© 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. 10-RES-JB
    11. 15965
    Prev
    Next
    INDEX
    Explanations

    sentences related to sports games and performances

    oai_token-act-pair · gpt-3.5-turbo

    statements expressing disappointment or missed opportunities

    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
    pires
    -0.85
    reprene
    -0.77
    scribe
    -0.72
     awaits
    -0.71
     millennia
    -0.70
     descendants
    -0.66
    onym
    -0.66
     expires
    -0.65
    osponsors
    -0.65
     forbids
    -0.64
    POSITIVE LOGITS
     lacked
    1.10
    Overall
    1.10
    didn
    1.06
     Overall
    0.98
     didnt
    0.97
    Was
    0.94
     didn
    0.87
     Ended
    0.86
     wasn
    0.86
     deserved
    0.83
    Activations Density 0.576%

    No Known Activations