© 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. 8186
    Prev
    Next
    INDEX
    Explanations

    names or terms related to a specific individual named Shay

    oai_token-act-pair · gpt-3.5-turbo
    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
    clerosis
    -0.78
    hester
    -0.75
    ocobo
    -0.73
     hemorrh
    -0.73
     Daredevil
    -0.70
    ffic
    -0.65
    iment
    -0.65
    ision
    -0.64
    itals
    -0.63
    ITED
    -0.63
    POSITIVE LOGITS
     Shay
    1.05
    witz
    0.80
    ton
    0.75
    bots
    0.75
    forth
    0.75
    renheit
    0.75
    te
    0.74
    ty
    0.74
    bridge
    0.73
    ety
    0.73
    Activations Density 0.011%

    No Known Activations