© 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. 2-RES-JB
    11. 8143
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific person named Dean in the text

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Dean."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TOR
    -0.92
    atoon
    -0.89
    stanbul
    -0.83
    ramid
    -0.82
    ickr
    -0.81
     circulate
    -0.75
    orsi
    -0.74
    uyomi
    -0.73
    isconsin
    -0.71
    raltar
    -0.70
    POSITIVE LOGITS
     Winchester
    1.06
     Dean
    0.88
     Beam
    0.79
     Ambrose
    0.78
    Dean
    0.78
     Warden
    0.74
    uate
    0.71
    uates
    0.70
    holder
    0.69
    stown
    0.69
    Activations Density 0.007%

    No Known Activations