© 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. 1-RES-JB
    11. 9500
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to a specific individual

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals' names, particularly those associated with a significant event or controversy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lihood
    -0.92
    es
    -0.72
     Veg
    -0.71
    chal
    -0.70
    eed
    -0.67
    ees
    -0.66
     Kend
    -0.65
     cha
    -0.64
     Corpus
    -0.63
    esity
    -0.63
    POSITIVE LOGITS
    flush
    0.88
    adeon
    0.88
    strip
    0.79
    ategic
    0.79
    itamin
    0.77
    ushing
    0.76
    utor
    0.76
    chnology
    0.74
    ogun
    0.72
    ouses
    0.70
    Activations Density 0.025%

    No Known Activations