© 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. 14419
    Prev
    Next
    INDEX
    Explanations

    references to religious concepts or titles

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "canon" in various contexts

    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
    Drug
    -0.89
    Õ
    -0.75
    sie
    -0.72
    AIDS
    -0.68
    Psych
    -0.68
     Dreams
    -0.68
    rador
    -0.66
    Soft
    -0.66
    ALTH
    -0.65
    Methods
    -0.64
    POSITIVE LOGITS
     canon
    1.20
    icals
    1.13
    canon
    1.11
     Canon
    1.07
    icity
    1.03
    ical
    0.98
     canonical
    0.97
    icles
    0.91
    ically
    0.89
    alogue
    0.87
    Activations Density 0.013%

    No Known Activations