© 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. 0-RES-JB
    11. 5241
    Prev
    Next
    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turbo

    repeated numerical sequences or time-related data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     blessing
    -0.69
     stubborn
    -0.69
     chast
    -0.67
     merciless
    -0.65
     encouragement
    -0.64
     unpopular
    -0.61
     disappro
    -0.61
     peg
    -0.61
     indefinitely
    -0.60
     discipl
    -0.60
    POSITIVE LOGITS
    00
    3.85
    0010
    2.02
    008
    2.01
    01
    1.99
    005
    1.99
    002
    1.94
    00000
    1.93
    006
    1.92
    000
    1.90
    004
    1.88
    Activations Density 0.016%

    No Known Activations