© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 6578
    Prev
    Next
    INDEX
    Explanations

    verbs denoting action or change

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate purpose or intention

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -0.57
     packets
    -0.52
    Ĥª
    -0.51
    hops
    -0.48
     Lines
    -0.48
    tun
    -0.47
    SourceFile
    -0.47
    listed
    -0.46
    hur
    -0.45
    need
    -0.45
    POSITIVE LOGITS
    ggles
    0.91
     minimize
    0.90
     maximize
    0.89
     accommodate
    0.89
     ensure
    0.89
     satisfy
    0.88
     avoid
    0.87
    ilet
    0.87
     conserve
    0.85
     give
    0.85
    Activations Density 0.940%

    No Known Activations