© 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. 1-RES-JB
    11. 11268
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or political documents or actions

    oai_token-act-pair · gpt-3.5-turbo

    references to legislation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erd
    -0.80
     Canal
    -0.74
     Verb
    -0.71
    vas
    -0.67
    lighting
    -0.67
    Var
    -0.67
     Islands
    -0.65
     Forsaken
    -0.65
     Sul
    -0.64
     Voy
    -0.63
    POSITIVE LOGITS
     legislation
    1.14
    interstitial
    1.08
    ĸļ
    0.98
     enacted
    0.93
     enforcement
    0.92
    ively
    0.90
    iard
    0.90
     legisl
    0.88
    ional
    0.85
    arians
    0.84
    Activations Density 0.013%

    No Known Activations