© 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. 10-RES-JB
    11. 6586
    Prev
    Next
    INDEX
    Explanations

    dates in history

    oai_token-act-pair · gpt-3.5-turbo

    references to years, particularly in the context of historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.72
    EStream
    -0.70
    atem
    -0.58
    malink
    -0.57
     classified
    -0.55
    phabet
    -0.55
     voic
    -0.55
    netflix
    -0.55
     buck
    -0.55
     Stall
    -0.55
    POSITIVE LOGITS
    86
    1.31
    89
    1.30
    92
    1.28
    96
    1.27
    87
    1.26
    85
    1.25
    76
    1.25
    98
    1.24
    91
    1.24
    82
    1.24
    Activations Density 0.054%

    No Known Activations