© 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. 8-RES-JB
    11. 17841
    Prev
    Next
    INDEX
    Explanations

    phrases related to separation or differences

    oai_token-act-pair · gpt-3.5-turbo

    instances of rivalry or conflict between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     landfall
    -0.79
    HCR
    -0.74
    士
    -0.71
     inund
    -0.69
    livion
    -0.67
     shelters
    -0.65
     emergencies
    -0.65
    vasive
    -0.64
     epidemic
    -0.62
    recated
    -0.61
    POSITIVE LOGITS
     Both
    1.44
    Both
    1.35
     Differences
    1.23
     respectively
    1.17
     Neither
    1.14
     mutually
    1.10
     Together
    1.02
     respective
    1.01
    each
    1.00
     Each
    1.00
    Activations Density 0.840%

    No Known Activations