© 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. 6-RES-JB
    11. 364
    Prev
    Next
    INDEX
    Explanations

    mentions of family members, particularly younger ones

    oai_token-act-pair · gpt-3.5-turbo

    references to younger individuals or generations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orial
    -0.81
    Syn
    -0.75
    place
    -0.73
    DCS
    -0.69
    ãĥ¼ãĥ
    -0.69
    odium
    -0.67
    places
    -0.65
    atro
    -0.64
    Ble
    -0.64
    election
    -0.63
    POSITIVE LOGITS
     generations
    1.07
     sibling
    1.06
     versions
    1.04
     brother
    1.00
     siblings
    0.97
     than
    0.93
     sister
    0.92
     adulthood
    0.90
     generation
    0.87
     puberty
    0.84
    Activations Density 0.019%

    No Known Activations