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. 20248
    Prev
    Next
    INDEX
    Explanations

    complex terms related to various aspects of social, political, and environmental issues

    oai_token-act-pair · gpt-3.5-turbo

    nouns that indicate various processes, actions, or situations

    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
    ACTED
    -0.61
     Cutter
    -0.59
    termination
    -0.54
    racuse
    -0.54
    Delivery
    -0.54
    lished
    -0.53
     Courier
    -0.53
    rency
    -0.52
    PDATE
    -0.52
     Writ
    -0.51
    POSITIVE LOGITS
     aren
    1.18
     are
    1.15
     belong
    1.12
     represent
    1.11
     weren
    1.07
     deserve
    1.07
     constitute
    1.03
     were
    1.03
     exist
    1.01
     ARE
    1.00
    Activations Density 0.197%

    No Known Activations