© 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. 1884
    Prev
    Next
    INDEX
    Explanations

    mentions of adolescents or teenagers

    oai_token-act-pair · gpt-3.5-turbo

    references to teenagers and adolescent-related themes

    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
    ktop
    -0.93
    daq
    -0.89
    itsch
    -0.88
     Canaver
    -0.84
    ichick
    -0.81
    atre
    -0.80
    ĪĴ
    -0.79
    adr
    -0.79
    vernment
    -0.78
    odcast
    -0.78
    POSITIVE LOGITS
     boys
    0.96
     girls
    0.92
    aged
    0.86
    agers
    0.86
    olesc
    0.85
     teenagers
    0.81
     daughters
    0.78
     adolesc
    0.77
     males
    0.77
    uates
    0.77
    Activations Density 0.010%

    No Known Activations