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. 7-RES-JB
    6. 92
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or legislative documents

    oai_token-act-pair · gpt-3.5-turbo

    plural nouns and specific acronyms related to specific topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cir
    -0.67
     mileage
    -0.65
     seas
    -0.65
    ////////
    -0.60
     Borough
    -0.60
    ãĤ´ãĥ³
    -0.60
     srfAttach
    -0.59
     dehydration
    -0.59
    potion
    -0.59
     Lur
    -0.59
    POSITIVE LOGITS
    ources
    0.94
    ervatives
    0.87
    acks
    0.84
    wana
    0.83
    olutions
    0.81
    ouls
    0.81
     alike
    0.80
    ixel
    0.79
    Ns
    0.79
    atically
    0.77
    Activations Density 0.146%

    No Known Activations