© 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. 7-RES-JB
    11. 11614
    Prev
    Next
    INDEX
    Explanations

    references to a specific politician named Paul Ryan

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Paul Ryan

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oscope
    -0.76
     hypers
    -0.73
    tainment
    -0.72
    eatures
    -0.67
    orative
    -0.65
    rees
    -0.64
    oslav
    -0.64
     Atlantis
    -0.63
    umbnails
    -0.62
     Britann
    -0.61
    POSITIVE LOGITS
     Zin
    0.81
    hof
    0.80
    airs
    0.70
    tti
    0.70
    gren
    0.69
    cloth
    0.68
     hugs
    0.67
    zona
    0.66
    interstitial
    0.66
    sels
    0.66
    Activations Density 0.007%

    No Known Activations