© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2500
    Prev
    Next
    INDEX
    Explanations

    references to teenage-related content

    oai_token-act-pair · gpt-3.5-turbo

    references to "teen" or "teenage" in various contexts

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

    No Comments

    Negative Logits
    mble
    -1.01
    choes
    -0.77
    xual
    -0.77
    leased
    -0.77
    */(
    -0.71
    adr
    -0.69
    lda
    -0.69
    cemic
    -0.68
    itsch
    -0.66
    é¾
    -0.66
    POSITIVE LOGITS
    age
    1.24
    agers
    1.15
    aged
    0.99
    ager
    0.95
     Teen
    0.94
     Titans
    0.93
    ish
    0.88
    ety
    0.88
    ishly
    0.87
    Teen
    0.87
    Activations Density 0.005%

    No Known Activations