© 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. 11-RES-JB
    11. 22636
    Prev
    Next
    INDEX
    Explanations

    mentions of large entities or organizations like companies or businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to companies and businesses in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    othy
    -0.78
    ultimate
    -0.77
    izoph
    -0.77
    theless
    -0.77
    ife
    -0.72
    rontal
    -0.71
    othes
    -0.69
    icter
    -0.68
    ople
    -0.68
    obia
    -0.68
    POSITIVE LOGITS
     headquartered
    1.24
     employing
    1.12
     operating
    1.04
     investing
    0.99
     vying
    0.99
     owning
    0.99
     reliant
    0.96
     suing
    0.95
     specializing
    0.95
     exporting
    0.95
    Activations Density 0.181%

    No Known Activations