© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10-RES-JB
    11. 7308
    Prev
    Next
    INDEX
    Explanations

    specific ages and medical conditions, particularly cancer diagnoses

    oai_token-act-pair · gpt-3.5-turbo

    references to ages and milestones in life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itivity
    -0.68
    EEE
    -0.68
    planes
    -0.67
    inals
    -0.67
    HTTP
    -0.67
    audi
    -0.66
    itized
    -0.65
    INAL
    -0.65
    ful
    -0.63
    pmwiki
    -0.63
    POSITIVE LOGITS
     age
    1.62
     puberty
    1.19
     ages
    1.06
     Age
    1.06
     birth
    1.02
    Age
    0.93
     adulthood
    0.90
    yp
    0.90
     Ages
    0.89
     childbirth
    0.88
    Activations Density 0.111%

    No Known Activations