© 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. 10-RES-JB
    11. 20456
    Prev
    Next
    INDEX
    Explanations

    references to specific historical decades followed by contextual elements or cultural references

    oai_token-act-pair · gpt-3.5-turbo

    references to specific decades and their associated cultural elements or artifacts

    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
    rollment
    -0.79
    alys
    -0.77
    iasis
    -0.77
    REDACTED
    -0.76
    pees
    -0.74
     contracting
    -0.74
    acts
    -0.74
    Contents
    -0.74
    hran
    -0.73
    lying
    -0.73
    POSITIVE LOGITS
    -'
    1.05
     vintage
    0.99
     classic
    0.97
     classics
    0.96
     Plymouth
    0.91
     Victorian
    0.90
     Era
    0.90
     Chevy
    0.90
     nostalgia
    0.88
     era
    0.87
    Activations Density 0.135%

    No Known Activations