© 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. 7903
    Prev
    Next
    INDEX
    Explanations

    mentions of specific individuals by name combined with a position or title

    oai_token-act-pair · gpt-3.5-turbo

    the presence of names that start with "Ade."

    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
    ipeg
    -0.85
    ivity
    -0.80
    urers
    -0.76
    lessness
    -0.70
    enegger
    -0.66
    orem
    -0.66
    sburgh
    -0.66
    urally
    -0.66
    iew
    -0.66
    imation
    -0.66
    POSITIVE LOGITS
    lled
    0.92
    cki
    0.85
    llan
    0.82
    vice
    0.79
    lli
    0.78
    lla
    0.78
    hani
    0.76
    utic
    0.73
    aways
    0.72
    hyde
    0.72
    Activations Density 0.040%

    No Known Activations