© 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 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. 9-RES-JB
    11. 19991
    Prev
    Next
    INDEX
    Explanations

    terms related to recent events, such as births, deaths, achievements, and announcements

    oai_token-act-pair · gpt-3.5-turbo

    references to crime and legal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vae
    -0.64
    })
    -0.61
     tended
    -0.61
    uez
    -0.59
    rely
    -0.59
    ļ
    -0.57
    )=
    -0.56
     thereto
    -0.55
    ŀ
    -0.55
     USSR
    -0.55
    POSITIVE LOGITS
     tonight
    1.00
     tomorrow
    0.89
     TODAY
    0.89
    !!!!
    0.88
     hoping
    0.85
     today
    0.85
    !
    0.84
    !!!
    0.81
     anytime
    0.79
     alongside
    0.76
    Activations Density 0.789%

    No Known Activations