© 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. 10227
    Prev
    Next
    INDEX
    Explanations

    words related to hypnosis

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "hypothesis" or "hypothetical" situations

    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
    ãģ®éŃĶ
    -0.90
    Gameplay
    -0.84
     Observer
    -0.80
    AUT
    -0.78
    FORE
    -0.78
     IMAGES
    -0.77
    姫
    -0.76
    UTERS
    -0.74
     Loans
    -0.72
    Constructed
    -0.71
    POSITIVE LOGITS
     hyp
    1.55
    nosis
    1.07
    hyp
    1.03
    Hyp
    0.93
    emic
    0.91
    ogly
    0.91
    oxic
    0.89
     horm
    0.89
    emonic
    0.88
     carbohyd
    0.87
    Activations Density 0.006%

    No Known Activations