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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 1520
    Prev
    Next
    INDEX
    Explanations

    specific mentions of the word "Land"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Land" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IBLE
    -0.87
     toler
    -0.71
    uates
    -0.70
     incons
    -0.68
    uously
    -0.68
     debilitating
    -0.67
    OPLE
    -0.67
     prov
    -0.67
     sight
    -0.66
    âĶĢâĶĢ
    -0.66
    POSITIVE LOGITS
     Force
    1.02
     Suit
    1.00
    Force
    0.97
    bringer
    0.96
     Fighters
    0.96
     Rover
    0.94
    yer
    0.91
     Matters
    0.89
    lord
    0.88
     Club
    0.86
    Activations Density 0.124%

    No Known Activations