© 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. 3586
    Prev
    Next
    INDEX
    Explanations

    locations specified by abbreviations such as 'IL' and 'HI'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the state of Illinois

    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
    uyomi
    -0.91
    dates
    -0.81
    bourg
    -0.79
    ambers
    -0.76
    lain
    -0.75
    oÄŁ
    -0.72
    Ü
    -0.72
    ¯¯
    -0.71
     Scientific
    -0.70
    nces
    -0.70
    POSITIVE LOGITS
     IL
    1.05
    inois
    1.03
    ibrary
    0.79
    enium
    0.78
    cember
    0.75
    UTION
    0.73
    rafted
    0.69
     rehearsal
    0.68
    wei
    0.68
     valve
    0.67
    Activations Density 0.011%

    No Known Activations