Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 2075
    Prev
    Next
    INDEX
    Explanations

    interactive elements and features

    oai_token-act-pair · gpt-3.5-turbo

    elements related to interactivity and animations in content

    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
    aido
    -0.86
    aligned
    -0.85
    abiding
    -0.83
    words
    -0.80
    ports
    -0.79
    ibel
    -0.78
    vere
    -0.78
    uters
    -0.77
    anship
    -0.77
    olit
    -0.77
    POSITIVE LOGITS
     memorial
    0.94
     version
    0.92
     replica
    0.88
     billboard
    0.88
     mock
    0.86
     kios
    0.84
     versions
    0.83
     wheelchair
    0.83
     scoreboard
    0.82
     GIF
    0.80
    Activations Density 0.200%

    No Known Activations