© 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. 18673
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical structures like stands or stands in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to stands in various contexts

    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
    EStream
    -0.78
    uliffe
    -0.66
     DNA
    -0.62
     disemb
    -0.61
     redacted
    -0.59
    ogram
    -0.58
     dementia
    -0.58
     havoc
    -0.57
    ersive
    -0.57
     negatively
    -0.56
    POSITIVE LOGITS
    ards
    0.96
    still
    0.92
    ardless
    0.92
    stand
    0.90
    psons
    0.80
    BuyableInstoreAndOnline
    0.79
    ingly
    0.78
    about
    0.77
    ages
    0.77
    s
    0.77
    Activations Density 0.006%

    No Known Activations