Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 15153
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and mathematical symbols

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating age or time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Choice
    -1.10
    Energy
    -1.04
    SPONSORED
    -1.03
    Individual
    -1.02
    Government
    -1.02
    Technical
    -1.00
    Application
    -0.99
    Parents
    -0.98
    Position
    -0.98
    Character
    -0.98
    POSITIVE LOGITS
     aust
    1.28
     americ
    1.22
     mir
    1.18
     sab
    1.17
     john
    1.17
     david
    1.16
     coh
    1.14
     sar
    1.14
     vic
    1.14
     sam
    1.12
    Activations Density 0.408%

    No Known Activations