© 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. 10-RES-JB
    11. 2815
    Prev
    Next
    INDEX
    Explanations

    words related to specific software programs or technology companies

    oai_token-act-pair · gpt-3.5-turbo

    brand or product names in the context of content consumption or media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     former
    -0.73
    etheless
    -0.70
     grounds
    -0.68
     condemned
    -0.67
     pressed
    -0.66
     divided
    -0.66
     dividing
    -0.65
     reconciliation
    -0.65
     judgment
    -0.65
     designated
    -0.64
    POSITIVE LOGITS
    Tech
    1.04
    Coin
    1.04
    itech
    0.99
    abit
    0.96
    Cam
    0.95
    isoft
    0.95
    atech
    0.95
    Forge
    0.94
    Chat
    0.93
    Apps
    0.93
    Activations Density 0.306%

    No Known Activations