Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 19895
    Prev
    Next
    INDEX
    Explanations

    mentions of evolutionary biology related terms, specifically ancestral and evolutionary concepts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ancestry and evolutionary heritage

    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
    bull
    -0.81
    atility
    -0.75
    eye
    -0.75
    ilde
    -0.75
    esc
    -0.72
    oun
    -0.70
    aughty
    -0.70
    jab
    -0.70
    acity
    -0.70
    awar
    -0.70
    POSITIVE LOGITS
     Ancest
    0.97
     ancestors
    0.96
     ancestor
    0.90
     ancestry
    0.89
    alogy
    0.89
     ancest
    0.87
     ancestral
    0.85
     lineage
    0.83
     descendant
    0.80
     Homo
    0.76
    Activations Density 0.043%

    No Known Activations