© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 12853
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to people, places, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate actions or events occurring over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antage
    -0.76
    ologies
    -0.73
     assumes
    -0.70
     substrate
    -0.70
     consumes
    -0.70
    rates
    -0.69
     governs
    -0.68
     improves
    -0.68
    lies
    -0.68
     relates
    -0.67
    POSITIVE LOGITS
    EStream
    0.68
     looph
    0.68
     Borough
    0.68
     Stage
    0.68
     Kinn
    0.67
     psychiat
    0.66
    cffffcc
    0.66
     aback
    0.65
     last
    0.64
     wiret
    0.64
    Activations Density 2.370%

    No Known Activations