© 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. 8545
    Prev
    Next
    INDEX
    Explanations

    verbs that denote actions or processes

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and other verbs that indicate actions or ongoing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    eria
    -0.74
    ana
    -0.73
    UI
    -0.72
    youtube
    -0.72
    eg
    -0.70
    IE
    -0.70
    UG
    -0.67
    ena
    -0.67
    ocl
    -0.67
    .–
    -0.67
    POSITIVE LOGITS
     them
    0.76
     instead
    0.72
     accordingly
    0.70
     untold
    0.69
     homage
    0.69
     unsus
    0.68
     nods
    0.66
     comparisons
    0.66
     only
    0.66
     whoever
    0.64
    Activations Density 0.332%

    No Known Activations