© 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. 3625
    Prev
    Next
    INDEX
    Explanations

    phrases related to prestigious accolades or institutions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to prestige and high status

    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
    Phones
    -0.69
    hy
    -0.68
    sil
    -0.66
    Twe
    -0.66
    calling
    -0.65
    Pod
    -0.63
    etc
    -0.62
    Rog
    -0.61
    laun
    -0.61
    hs
    -0.60
    POSITIVE LOGITS
     prestigious
    1.16
     accol
    0.99
     honors
    0.92
     awards
    0.87
     sophistic
    0.83
     citiz
    0.82
    AFTA
    0.82
     prestige
    0.81
     Institution
    0.81
     institution
    0.79
    Activations Density 0.010%

    No Known Activations