© 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. 2-RES-JB
    11. 23885
    Prev
    Next
    INDEX
    Explanations

    mentions of people's names, particularly with the surname "Robertson"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those involved in political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UME
    -0.69
    spring
    -0.68
    usp
    -0.68
     Romantic
    -0.67
    udic
    -0.62
    ymes
    -0.61
    URE
    -0.61
    aternity
    -0.61
    ERE
    -0.61
    Drug
    -0.59
    POSITIVE LOGITS
     Robertson
    0.99
    igon
    0.95
    kinson
    0.92
    oute
    0.88
    ©¶æ¥µ
    0.82
    yssey
    0.81
    sey
    0.81
    onite
    0.79
    iets
    0.76
     Broadcasting
    0.75
    Activations Density 0.008%

    No Known Activations