© 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. 9-RES-JB
    11. 9066
    Prev
    Next
    INDEX
    Explanations

    mentions of a person named Drew

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Drew"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¿
    -0.72
    utra
    -0.71
    opsy
    -0.70
    ãĤ³
    -0.70
    ãĤ¹ãĥĪ
    -0.69
    Enlarge
    -0.67
     suspic
    -0.67
    ãĤ¶
    -0.64
     redistributed
    -0.63
    OTOS
    -0.63
    POSITIVE LOGITS
     Brees
    1.32
    rite
    0.96
    nesday
    0.95
     Estate
    0.95
    ritten
    0.94
     Carey
    0.93
     Ange
    0.90
    driver
    0.85
    ey
    0.84
    bles
    0.83
    Activations Density 0.047%

    No Known Activations