© 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. 2-RES-JB
    11. 12916
    Prev
    Next
    INDEX
    Explanations

    mentions of ancestral or evolutionary connections

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ancestry and family lineage

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RH
    -0.81
    IFF
    -0.74
    "]=>
    -0.69
    urrent
    -0.68
    housing
    -0.68
    Rated
    -0.66
    awar
    -0.65
    HUD
    -0.64
    esc
    -0.64
    amina
    -0.64
    POSITIVE LOGITS
     ancestor
    1.30
     ancestors
    1.29
     Ancest
    1.04
     ancestry
    0.93
     ancestral
    0.91
     lineage
    0.91
     descendant
    0.83
     ancest
    0.82
    alogy
    0.80
     worsh
    0.78
    Activations Density 0.013%

    No Known Activations