© 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. 4-RES-JB
    11. 23689
    Prev
    Next
    INDEX
    Explanations

    words related to urging or encouraging actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that direct or urge action towards specific subjects

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

    No Comments

    Negative Logits
    _.
    -0.71
     Detected
    -0.68
    traumatic
    -0.67
    holes
    -0.65
     Appears
    -0.65
    washer
    -0.62
    closed
    -0.60
     Yep
    -0.60
    quickShipAvailable
    -0.60
    cloth
    -0.59
    POSITIVE LOGITS
     avoid
    1.03
     participate
    0.98
     undertake
    0.97
     minimize
    0.93
     keep
    0.93
     reconsider
    0.92
     emulate
    0.92
     learn
    0.91
     maximize
    0.91
     embrace
    0.91
    Activations Density 0.210%

    No Known Activations