© 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. 9-RES-JB
    11. 15362
    Prev
    Next
    INDEX
    Explanations

    phrases related to computer performance and optimization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to performance metrics and issues in computing or technology

    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
    ril
    -0.86
    ocent
    -0.84
    sonian
    -0.84
    ICLE
    -0.77
    erville
    -0.74
    ovie
    -0.72
    orical
    -0.71
    orial
    -0.71
    een
    -0.69
     Ending
    -0.68
    POSITIVE LOGITS
     optimizations
    1.35
     optimization
    1.16
     improvements
    1.03
     efficiency
    0.98
     degradation
    0.96
    iencies
    0.95
     thrott
    0.95
     advantages
    0.95
     throughput
    0.93
    efficiency
    0.93
    Activations Density 0.127%

    No Known Activations