© 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. 8-RES-JB
    11. 2778
    Prev
    Next
    INDEX
    Explanations

    mentions of historical figures or texts, particularly from literary or academic contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to historical literary works and notable authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amacare
    -0.98
     Obamacare
    -0.96
     ObamaCare
    -0.96
    oppable
    -0.90
    CEO
    -0.89
     POLITICO
    -0.85
     millennials
    -0.83
     CEOs
    -0.83
     hurting
    -0.82
     Millennials
    -0.81
    POSITIVE LOGITS
     histor
    1.22
     manuscript
    1.17
     manuscripts
    1.16
     historians
    1.15
     unpublished
    1.15
    ibliography
    1.13
     historian
    1.12
     Hist
    1.12
     inscription
    1.12
     interpol
    1.10
    Activations Density 1.297%

    No Known Activations