© 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. 6-RES-JB
    11. 15544
    Prev
    Next
    INDEX
    Explanations

    phrases related to research and development

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions related to research and development contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hov
    -0.92
    ukong
    -0.87
    ouls
    -0.82
    nikov
    -0.80
    hatt
    -0.75
     Loren
    -0.73
    cipled
    -0.71
    atonin
    -0.70
    acci
    -0.68
    utra
    -0.67
    POSITIVE LOGITS
     maintenance
    0.97
     evaluation
    0.87
     subsistence
    0.85
     dissemination
    0.83
     processing
    0.83
     disposal
    0.82
     exploitation
    0.79
     communication
    0.79
     debugging
    0.78
     logistics
    0.78
    Activations Density 0.318%

    No Known Activations