© 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. 8-RES-JB
    11. 17204
    Prev
    Next
    INDEX
    Explanations

    present perfect tense verbs

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating occurrences or events that have happened

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pressuring
    -0.69
     projecting
    -0.67
     plotting
    -0.66
     undertaking
    -0.66
     wasting
    -0.64
     preparing
    -0.64
     stripping
    -0.64
     incapable
    -0.63
     sending
    -0.63
     delusion
    -0.61
    POSITIVE LOGITS
    abouts
    0.90
    ivably
    0.78
    enty
    0.74
    rolet
    0.74
    emonium
    0.73
    umerable
    0.72
    umerous
    0.70
     been
    0.70
     arisen
    0.69
    always
    0.69
    Activations Density 0.112%

    No Known Activations