© 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. 7-RES-JB
    11. 22850
    Prev
    Next
    INDEX
    Explanations

    tech companies and related entities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of major technology and internet companies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adjourn
    -0.72
     lik
    -0.68
     contagious
    -0.67
     deaf
    -0.66
     kay
    -0.59
     warranty
    -0.59
     Investigator
    -0.58
    ioned
    -0.57
    onym
    -0.57
    endum
    -0.56
    POSITIVE LOGITS
     respectively
    0.87
     alike
    0.80
    BSD
    0.79
     etc
    0.78
    MSN
    0.75
     cartels
    0.74
    opol
    0.73
    Gaming
    0.73
    NL
    0.69
    soDeliveryDate
    0.68
    Activations Density 0.278%

    No Known Activations