© 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. 9953
    Prev
    Next
    INDEX
    Explanations

    references to computer memory-related concepts or issues

    oai_token-act-pair · gpt-3.5-turbo

    references to memory usage and management in computing

    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
    jon
    -0.78
     Riy
    -0.74
    Ļ½
    -0.72
    »
    -0.71
    isco
    -0.70
     Grimm
    -0.70
    yright
    -0.69
     Pearce
    -0.68
    bara
    -0.67
     Reef
    -0.65
    POSITIVE LOGITS
     allocation
    1.09
     bandwidth
    0.95
     allocations
    0.95
     subsystem
    0.93
     storage
    0.91
    disk
    0.90
     allocated
    0.90
     dumps
    0.89
    Pool
    0.88
     fragmentation
    0.87
    Activations Density 0.033%

    No Known Activations