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. 9-RES-JB
    6. 12339
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing something to different groups or entities

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the provision of services or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    former
    -0.73
    usa
    -0.70
    leave
    -0.64
    AU
    -0.64
    NPR
    -0.64
    fox
    -0.64
    ABC
    -0.63
    orp
    -0.62
    NN
    -0.61
    kind
    -0.59
    POSITIVE LOGITS
     regards
    1.08
     regard
    0.95
    stood
    0.92
     sufficient
    0.91
     respect
    0.90
     impunity
    0.87
     ample
    0.81
    ãĥīãĥ©ãĤ´ãĥ³
    0.79
    draw
    0.79
     tons
    0.78
    Activations Density 0.154%

    No Known Activations