© 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. 10217
    Prev
    Next
    INDEX
    Explanations

    political terms and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to large groups of people or collective sentiments

    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
    runtime
    -0.80
    gery
    -0.80
    ĸļ
    -0.77
    itary
    -0.73
    ibal
    -0.69
    ë
    -0.68
    oise
    -0.66
    application
    -0.66
    othy
    -0.65
    XL
    -0.65
    POSITIVE LOGITS
     observers
    1.18
     analysts
    1.08
     lawmakers
    1.06
     commentators
    1.02
     speculate
    1.00
     commenters
    1.00
     critics
    0.95
     conservatives
    0.95
     speculated
    0.94
     argue
    0.93
    Activations Density 0.167%

    No Known Activations