© 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. 4-RES-JB
    11. 22322
    Prev
    Next
    INDEX
    Explanations

    the name "Steyer" with various prefixes and suffixes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Steyer."

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

    No Comments

    Negative Logits
    etheless
    -0.79
    IFIED
    -0.74
     eleph
    -0.74
    schild
    -0.72
    OUNT
    -0.71
     Kod
    -0.71
     GOODMAN
    -0.70
    姫
    -0.67
    tan
    -0.67
    enegger
    -0.67
    POSITIVE LOGITS
    uben
    0.98
    pping
    0.94
    ering
    0.89
    acher
    0.88
    pped
    0.84
    chnology
    0.84
    ste
    0.83
    arde
    0.83
    ck
    0.83
    aling
    0.82
    Activations Density 0.008%

    No Known Activations