© 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. 4523
    Prev
    Next
    INDEX
    Explanations

    references to a person named "Tyler."

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Tyler."

    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
    ãĥīãĥ©
    -0.74
     actionGroup
    -0.72
    ãĤ¦ãĤ¹
    -0.71
    schild
    -0.68
    edition
    -0.68
    gotten
    -0.67
    fm
    -0.66
     unfocusedRange
    -0.66
    Ö¼
    -0.66
    ãĤ»
    -0.65
    POSITIVE LOGITS
     Tyler
    1.13
     Wink
    0.95
     Shields
    0.84
    Tyler
    0.83
     Chandler
    0.81
     Templ
    0.80
     Vaugh
    0.80
     Skywalker
    0.79
    warm
    0.79
     Strait
    0.78
    Activations Density 0.009%

    No Known Activations