© 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. 10-RES-JB
    11. 21512
    Prev
    Next
    INDEX
    Explanations

    names or terms related to individuals named Vasquez and Ras

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly "Vasquez" and "Ras."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sie
    -0.64
    ycle
    -0.64
    OLOG
    -0.61
    payer
    -0.60
    ģĸ
    -0.58
    ĺħ
    -0.58
     grate
    -0.58
     Focus
    -0.57
    tted
    -0.57
     Drift
    -0.56
    POSITIVE LOGITS
    quez
    1.33
    sel
    1.15
    daq
    1.14
    heed
    1.05
    sell
    1.01
    sels
    0.99
    hes
    0.99
    hers
    0.97
    cul
    0.96
    her
    0.95
    Activations Density 0.047%

    No Known Activations