© 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. 1-RES-JB
    11. 5455
    Prev
    Next
    INDEX
    Explanations

    specific sequences of characters within a longer string

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "urs" related to collaborative efforts or community initiatives

    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
     Metatron
    -0.68
     Pend
    -0.66
     button
    -0.64
     machine
    -0.62
     Clarkson
    -0.61
     past
    -0.61
     Newton
    -0.60
     âĸł
    -0.60
     4096
    -0.57
    ISON
    -0.57
    POSITIVE LOGITS
    urs
    1.20
    hip
    1.11
    ury
    1.02
    ensical
    0.93
    rences
    0.93
     confir
    0.91
    geons
    0.91
    atile
    0.91
    vous
    0.89
    cript
    0.89
    Activations Density 0.006%

    No Known Activations