© 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. 2265
    Prev
    Next
    INDEX
    Explanations

    terms related to locations or physical centers

    oai_token-act-pair · gpt-3.5-turbo
    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
     chops
    -0.70
    >:
    -0.69
    >(
    -0.69
    >
    -0.66
    ially
    -0.64
     summ
    -0.63
    iko
    -0.62
    osponsors
    -0.61
     describ
    -0.60
    tim
    -0.60
    POSITIVE LOGITS
     gravity
    0.98
     attention
    0.97
     Attention
    0.88
     controversy
    0.86
     contention
    0.84
     controversies
    0.74
     excellence
    0.73
    Initialized
    0.73
     hostilities
    0.72
     largeDownload
    0.70
    Activations Density 0.078%

    No Known Activations