© 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. 7-RES-JB
    11. 20036
    Prev
    Next
    INDEX
    Explanations

    technical terms related to scientific experiments and equipment

    oai_token-act-pair · gpt-3.5-turbo

    scientific methodologies and technical terms related to experimental research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    女
    -0.78
     heirs
    -0.77
     Restaur
    -0.76
     Taxes
    -0.76
    ultural
    -0.74
     Rebell
    -0.73
     Retirement
    -0.70
     grievances
    -0.70
     Confederation
    -0.70
    bernatorial
    -0.69
    POSITIVE LOGITS
     scanning
    1.00
     scanner
    0.88
     tripod
    0.88
     infrared
    0.87
     microscope
    0.87
    scan
    0.86
     Leica
    0.84
     scan
    0.84
     telescope
    0.84
    oscope
    0.83
    Activations Density 0.596%

    No Known Activations