© 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. 3-RES-JB
    11. 12124
    Prev
    Next
    INDEX
    Explanations

    professor names at various universities

    oai_token-act-pair · gpt-3.5-turbo

    academic affiliations or titles associated with professors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curtains
    -0.87
    sticks
    -0.72
    ptoms
    -0.71
    boats
    -0.71
    photos
    -0.69
     rentals
    -0.66
    steam
    -0.66
    atari
    -0.65
     amen
    -0.65
     dots
    -0.65
    POSITIVE LOGITS
     specializing
    0.94
     studying
    0.92
     PhD
    0.90
     Applied
    0.86
     doctoral
    0.84
     universities
    0.78
     MIT
    0.76
     academia
    0.74
     university
    0.74
     researching
    0.74
    Activations Density 0.270%

    No Known Activations