© 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. 20494
    Prev
    Next
    INDEX
    Explanations

    words related to continuation or continuation of events

    oai_token-act-pair · gpt-3.5-turbo
    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
    ãĤ¬
    -0.74
    Reloaded
    -0.67
    pload
    -0.67
     Shed
    -0.64
    cffffcc
    -0.62
    Bee
    -0.62
     calves
    -0.61
    ======
    -0.60
    manship
    -0.60
     Knights
    -0.60
    POSITIVE LOGITS
    rived
    1.31
    ortion
    1.12
    ruction
    1.11
    ouring
    1.10
    ruct
    1.08
    ours
    1.06
    ending
    1.06
    rive
    1.05
    orting
    1.05
    rib
    1.04
    Activations Density 0.014%

    No Known Activations