© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 15576
    Prev
    Next
    INDEX
    Explanations

    mentions and discussions of memory in a computer system context

    oai_token-act-pair · gpt-3.5-turbo

    mentions of memory usage and related metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qqa
    -0.80
     Riy
    -0.76
    jon
    -0.73
    glers
    -0.72
    bara
    -0.71
    zag
    -0.71
    Ĭ±
    -0.70
    keye
    -0.70
    nen
    -0.69
    ŃĶ
    -0.69
    POSITIVE LOGITS
     allocation
    1.01
     storage
    0.91
     consolidation
    0.89
     dumps
    0.89
     utilization
    0.89
     bandwidth
    0.88
     allocations
    0.87
     subsystem
    0.86
     fragmentation
    0.85
     allocated
    0.83
    Activations Density 0.033%

    No Known Activations