© 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. 11-RES-JB
    11. 2454
    Prev
    Next
    INDEX
    Explanations

    quotes and statements by political figures

    oai_token-act-pair · gpt-3.5-turbo

    patterns of reporting or quotes from various sources and individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     murd
    -0.63
    gregation
    -0.63
    Monster
    -0.62
    iHUD
    -0.61
     orig
    -0.61
    Entity
    -0.61
     glim
    -0.60
    vag
    -0.60
    Mine
    -0.59
     Sioux
    -0.58
    POSITIVE LOGITS
     he
    1.12
     Putin
    0.98
     him
    0.95
     Netanyahu
    0.93
     Hollande
    0.89
     Modi
    0.88
     his
    0.88
     Obama
    0.85
     Merkel
    0.84
     Nieto
    0.84
    Activations Density 0.426%

    No Known Activations