© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 7948
    Prev
    Next
    INDEX
    Explanations

    phrases related to being suspended or being in a state of uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "hung."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":[
    -0.79
     Outbreak
    -0.74
     Table
    -0.72
    ASE
    -0.69
     Portal
    -0.67
    Wiki
    -0.66
    table
    -0.63
     Equal
    -0.63
     Explorer
    -0.60
    aez
    -0.60
    POSITIVE LOGITS
     hung
    3.73
     hangs
    2.46
     hang
    2.04
     hanging
    1.92
     hanged
    1.90
    hung
    1.81
     Hung
    1.25
     rested
    1.19
    hang
    1.13
    Hung
    1.08
    Activations Density 0.015%

    No Known Activations