© 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. 1-RES-JB
    11. 14583
    Prev
    Next
    INDEX
    Explanations

    mentions of revisiting or revising something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "revis" and its variations, indicating a focus on revisiting or reconsidering topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahi
    -0.86
    erb
    -0.73
    vin
    -0.72
    handle
    -0.70
    arel
    -0.67
    abet
    -0.67
    mpeg
    -0.65
    ain
    -0.63
    thing
    -0.62
    anto
    -0.62
    POSITIVE LOGITS
     revisit
    1.22
     revis
    1.03
    issance
    0.88
    PsyNetMessage
    0.81
    CLASSIFIED
    0.79
     replay
    0.78
    Discuss
    0.78
     recons
    0.77
     snapshots
    0.77
    ĸļ
    0.77
    Activations Density 0.005%

    No Known Activations