© 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. 3960
    Prev
    Next
    INDEX
    Explanations

    mentions of teenage individuals

    oai_token-act-pair · gpt-3.5-turbo

    references to teenagers or the teenage experience

    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
    SHIP
    -0.75
    leased
    -0.66
    ãģķ
    -0.65
    andum
    -0.63
    UTERS
    -0.63
    ãģ®å
    -0.63
     bilateral
    -0.62
     CODE
    -0.62
    ł
    -0.61
    ãģĤ
    -0.61
    POSITIVE LOGITS
    cape
    1.11
    uates
    0.94
    chool
    0.88
    olesc
    0.85
    kids
    0.84
    agers
    0.82
     teens
    0.82
    ager
    0.81
    zin
    0.79
    leeve
    0.78
    Activations Density 0.009%

    No Known Activations