© 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. 9-RES-JB
    11. 16179
    Prev
    Next
    INDEX
    Explanations

    phrases related to governmental levels or political contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to national or local governance and policy issues

    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
    uph
    -0.68
    raised
    -0.67
    selling
    -0.67
    wen
    -0.65
    adding
    -0.64
    fitting
    -0.63
    amera
    -0.62
     overfl
    -0.62
    ishly
    -0.61
    upon
    -0.61
    POSITIVE LOGITS
     outset
    1.28
     expense
    1.28
     behest
    1.20
     forefront
    1.14
     helm
    1.04
     moment
    0.97
     end
    0.97
     discretion
    0.94
     doorstep
    0.93
     beginning
    0.91
    Activations Density 0.110%

    No Known Activations