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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 4203
    Prev
    Next
    INDEX
    Explanations

    keywords related to physical locations, specifically headquarters

    oai_token-act-pair · gpt-3.5-turbo

    references to various organizational headquarters

    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
    erer
    -0.77
    flix
    -0.75
    ef
    -0.74
    spir
    -0.72
    cible
    -0.72
    ebook
    -0.69
    isher
    -0.67
    fall
    -0.67
    verbs
    -0.66
    nel
    -0.66
    POSITIVE LOGITS
     headquarters
    0.89
     building
    0.86
     Building
    0.81
     located
    0.80
    enture
    0.77
     Address
    0.77
     address
    0.76
     reception
    0.71
     premises
    0.71
     location
    0.71
    Activations Density 0.036%

    No Known Activations