© 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. 3-RES-JB
    11. 667
    Prev
    Next
    INDEX
    Explanations

    references to elite or exclusive entities

    oai_token-act-pair · gpt-3.5-turbo

    the term "elite" used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    giving
    -0.74
    externalActionCode
    -0.73
    ventory
    -0.70
    asta
    -0.69
     Drawn
    -0.68
    thus
    -0.68
    aul
    -0.66
    SourceFile
    -0.66
     Caption
    -0.66
    alone
    -0.65
    POSITIVE LOGITS
     mosqu
    0.98
     elite
    0.98
     academy
    0.81
     acad
    0.80
     Institution
    0.77
     athlete
    0.76
     elites
    0.73
     athletes
    0.73
     prep
    0.72
     unemploy
    0.72
    Activations Density 0.013%

    No Known Activations