© 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. 8-RES-JB
    11. 6358
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Teen" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to "teen" or "teenage" related content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mble
    -0.90
     lawy
    -0.76
    */(
    -0.76
    leased
    -0.75
    cemic
    -0.69
    lda
    -0.69
     rall
    -0.67
     freight
    -0.66
    itsch
    -0.66
    eger
    -0.66
    POSITIVE LOGITS
    agers
    1.24
    age
    1.23
    aged
    1.22
    ager
    1.11
    AGE
    0.97
    uates
    0.93
    ety
    0.91
    ages
    0.89
    aging
    0.88
    Nick
    0.86
    Activations Density 0.028%

    No Known Activations