© 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. 9-RES-JB
    11. 15723
    Prev
    Next
    INDEX
    Explanations

    situations where something new is being added to a context or list

    oai_token-act-pair · gpt-3.5-turbo

    instances of adding or contributing to a situation or context

    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
    /
    -0.67
    CBC
    -0.65
    Released
    -0.65
    Present
    -0.63
    EStream
    -0.63
    OSED
    -0.62
    Application
    -0.61
    published
    -0.61
    PLIED
    -0.61
    WR
    -0.59
    POSITIVE LOGITS
     thereto
    1.00
    endum
    0.97
     flair
    0.94
     dots
    0.90
     layer
    0.88
     extra
    0.87
     layers
    0.83
     onto
    0.82
     dimension
    0.82
     caveat
    0.80
    Activations Density 0.244%

    No Known Activations