© 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. 2-RES-JB
    11. 1073
    Prev
    Next
    INDEX
    Explanations

    phrases where someone is credited with writing something, such as books, articles, reports, or social media posts

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "wrote."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ĭ±
    -0.82
    xon
    -0.74
    Magn
    -0.70
    amac
    -0.67
    EGA
    -0.67
    Afee
    -0.67
    Enlarge
    -0.66
    phant
    -0.66
    OPA
    -0.65
    nor
    -0.63
    POSITIVE LOGITS
     penned
    0.84
     poems
    0.84
    writer
    0.82
     written
    0.81
    smanship
    0.81
    wrote
    0.79
     aloud
    0.79
     eloqu
    0.78
     memos
    0.78
    writ
    0.77
    Activations Density 0.034%

    No Known Activations