© 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. 20911
    Prev
    Next
    INDEX
    Explanations

    references to specific people or medical conditions, with a focus on autism

    oai_token-act-pair · gpt-3.5-turbo

    references to autistic individuals

    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
    ickey
    -0.76
     buoy
    -0.74
    olutions
    -0.70
    iquid
    -0.69
    itarian
    -0.68
    inosaur
    -0.67
     Peb
    -0.67
    é¾įå
    -0.65
    Downloadha
    -0.64
    ollar
    -0.63
    POSITIVE LOGITS
    elin
    0.78
    etta
    0.76
    ENA
    0.73
    anus
    0.69
     Pastebin
    0.69
    eq
    0.67
     allies
    0.66
    ENCY
    0.66
    TeX
    0.66
    EP
    0.66
    Activations Density 0.000%

    No Known Activations