© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6984
    Prev
    Next
    INDEX
    Explanations

    times and dates formatted in specific ways

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific volume or issue number in a publication

    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
     tradem
    -1.12
     srf
    -0.91
     conflic
    -0.91
    uations
    -0.88
    awaru
    -0.88
     volunte
    -0.83
    inates
    -0.79
     proport
    -0.77
    undai
    -0.77
     paved
    -0.74
    POSITIVE LOGITS
    87
    1.06
    81
    1.01
    88
    1.00
    83
    0.98
    11
    0.95
    07
    0.95
    77
    0.94
    82
    0.93
    08
    0.93
    61
    0.91
    Activations Density 0.036%

    No Known Activations