© 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 EvalsExportsinterp-engineNEWAPI 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. 7-RES-JB
    11. 14422
    Prev
    Next
    INDEX
    Explanations

    phrases related to prestigious awards and achievements

    oai_token-act-pair · gpt-3.5-turbo

    references to various awards and their categories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cos
    -0.72
     aber
    -0.71
    folk
    -0.70
     inconven
    -0.67
     enact
    -0.65
     embodiments
    -0.62
    ALTH
    -0.62
     CY
    -0.62
    essions
    -0.61
     nu
    -0.61
    POSITIVE LOGITS
     Winner
    1.01
     Winners
    0.98
     awarded
    0.97
    Winner
    0.96
     winner
    0.93
    Ĥİ
    0.92
     Prize
    0.91
    winning
    0.90
     Winning
    0.88
    inguished
    0.87
    Activations Density 0.037%

    No Known Activations