© 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. 20375
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features related to products or technology

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to performance and efficiency in technology

    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
     Marketable
    -0.80
    worn
    -0.78
    IRC
    -0.77
    married
    -0.77
    dress
    -0.76
    Male
    -0.75
    iddler
    -0.74
    atu
    -0.73
     Married
    -0.72
     Cosponsors
    -0.72
    POSITIVE LOGITS
     flexibility
    1.75
     reliability
    1.71
     usability
    1.68
     versatility
    1.67
     efficiency
    1.64
     durability
    1.61
     accuracy
    1.61
     stability
    1.59
     functionality
    1.58
     responsiveness
    1.58
    Activations Density 0.279%

    No Known Activations