© 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. 7025
    Prev
    Next
    INDEX
    Explanations

    phrases related to sports performance and statistics

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "has."

    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
    eem
    -0.63
    Enlarge
    -0.62
     Refer
    -0.62
    PC
    -0.62
     observing
    -0.61
     Apart
    -0.61
    OOL
    -0.61
     Hundred
    -0.60
     guid
    -0.59
    microsoft
    -0.59
    POSITIVE LOGITS
     been
    1.33
    been
    1.18
     undergone
    1.09
     struggled
    1.08
     gone
    1.05
     gotten
    1.02
     become
    1.01
     risen
    0.98
     battled
    0.93
     survived
    0.92
    Activations Density 0.203%

    No Known Activations