© 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. 23316
    Prev
    Next
    INDEX
    Explanations

    proper names starting with 'Br' or 'Br' pronounced phonetically, such as Brett and Bryce

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Brett."

    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
    Flow
    -0.78
    CVE
    -0.76
    shapeshifter
    -0.73
    EMS
    -0.71
    appropri
    -0.71
    horse
    -0.70
    ticket
    -0.70
    advert
    -0.70
    pir
    -0.70
    haps
    -0.69
    POSITIVE LOGITS
     Brett
    1.26
     Kavanaugh
    1.22
     Fav
    0.91
     Hod
    0.84
     Tucker
    0.83
     Rat
    0.83
     Gibson
    0.83
     Henderson
    0.80
     Wyatt
    0.80
    rett
    0.80
    Activations Density 0.007%

    No Known Activations