© 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. 3696
    Prev
    Next
    INDEX
    Explanations

    numerical values corresponding to episodes in a series

    oai_token-act-pair · gpt-3.5-turbo

    references to episode numbers of television shows or podcasts

    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
    sheets
    -0.91
    folk
    -0.88
    minist
    -0.82
    press
    -0.75
    gem
    -0.73
    don
    -0.72
    */(
    -0.71
     cycling
    -0.71
    ele
    -0.71
    ifi
    -0.71
    POSITIVE LOGITS
     Episode
    1.25
    Episode
    1.01
     Tickets
    0.82
    Stage
    0.82
     Transcript
    0.80
    isodes
    0.79
    episode
    0.78
     Surprise
    0.77
     Topics
    0.77
     Interview
    0.77
    Activations Density 0.019%

    No Known Activations