© 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. 7-RES-JB
    11. 18877
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or organizations named "Kings"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of a sports team named "Kings."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaru
    -0.81
    eredith
    -0.76
    zzle
    -0.69
    ierrez
    -0.69
    schild
    -0.68
    enegger
    -0.68
    llah
    -0.67
    astical
    -0.66
    ATIONAL
    -0.63
    urity
    -0.63
    POSITIVE LOGITS
    Kings
    0.99
    guard
    0.96
    north
    0.92
     Kings
    0.91
    bury
    0.90
    knife
    0.85
    hip
    0.84
    olver
    0.82
    mont
    0.80
    pool
    0.80
    Activations Density 0.027%

    No Known Activations