© 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. 10-RES-JB
    6. 11233
    Prev
    Next
    INDEX
    Explanations

    mentions of land or land-related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to land and its valuation or ownership

    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
    omatic
    -0.74
     laughter
    -0.72
    lycer
    -0.69
    ricular
    -0.69
    ĸļ
    -0.67
    ombies
    -0.65
    Inst
    -0.65
     Whip
    -0.63
    endo
    -0.63
     satirical
    -0.62
    POSITIVE LOGITS
     holdings
    1.23
    owner
    1.14
     leases
    1.02
     parcels
    1.02
     leased
    1.01
    owners
    0.99
    conservancy
    0.96
     adjoining
    0.96
     reclaimed
    0.96
     lease
    0.95
    Activations Density 0.081%

    No Known Activations