© 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. 17730
    Prev
    Next
    INDEX
    Explanations

    proper nouns typically associated with government agencies

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental or organizational agencies

    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
     impeachment
    -0.86
     impe
    -0.84
     lyr
    -0.72
     Phar
    -0.69
     rhy
    -0.68
     racer
    -0.68
     Gutenberg
    -0.67
     bog
    -0.66
     lamb
    -0.66
     spoilers
    -0.66
    POSITIVE LOGITS
    formerly
    1.31
    USA
    1.23
    which
    1.21
    NYSE
    1.21
    whose
    1.19
    now
    1.19
    NAS
    1.17
    UGC
    1.16
    MAC
    1.14
    WHO
    1.13
    Activations Density 0.048%

    No Known Activations