© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 20349
    Prev
    Next
    INDEX
    Explanations

    mentions of ancestors or ancestral relations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ancestry and lineage

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

    No Comments

    Negative Logits
    bull
    -0.77
    pmwiki
    -0.75
    esc
    -0.70
    Rated
    -0.69
    awar
    -0.68
    atur
    -0.68
    ftime
    -0.67
    campaign
    -0.65
    Asset
    -0.63
    atility
    -0.63
    POSITIVE LOGITS
     ancestor
    1.13
     ancestors
    1.03
     Ancest
    1.02
    alogy
    1.00
     ancestry
    0.94
     lineage
    0.92
     descendant
    0.86
     ancestral
    0.84
     ancest
    0.83
     worsh
    0.74
    Activations Density 0.020%

    No Known Activations