© 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. 3-RES-JB
    11. 11272
    Prev
    Next
    INDEX
    Explanations

    references to folk tales or stories passed down through generations

    oai_token-act-pair · gpt-3.5-turbo

    references to storytelling or narratives, particularly folk tales and their variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erate
    -0.94
    ividual
    -0.90
    bledon
    -0.83
    uters
    -0.80
    atever
    -0.79
    ervatives
    -0.78
    ulty
    -0.76
    itters
    -0.75
    eeks
    -0.75
    ournal
    -0.74
    POSITIVE LOGITS
     tale
    1.25
     tales
    1.24
     Tale
    1.06
    tale
    1.05
     Tales
    1.01
     Reincarn
    0.96
    Narr
    0.87
    tell
    0.86
    telling
    0.79
     Ragnarok
    0.79
    Activations Density 0.048%

    No Known Activations