© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 20263
    Prev
    Next
    INDEX
    Explanations

    political entities or public figures

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their actions or policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ³³³³³³³³³³³³³³³³
    -0.65
     Medline
    -0.63
    Ô
    -0.61
    ortium
    -0.57
    estern
    -0.57
    staking
    -0.57
     Pesh
    -0.54
     @
    -0.54
    ³³³³
    -0.54
     google
    -0.54
    POSITIVE LOGITS
     altogether
    0.83
     newcomers
    0.76
     foes
    0.76
     amid
    0.75
     goodies
    0.72
     alike
    0.71
     woes
    0.69
     elsewhere
    0.67
     orthodoxy
    0.67
     foe
    0.67
    Activations Density 1.123%

    No Known Activations