© 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. 0-RES-JB
    11. 6437
    Prev
    Next
    INDEX
    Explanations

    phrases related to social or economic underprivileged groups

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to preservation and underrepresentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiding
    -0.78
     raid
    -0.68
     SWAT
    -0.63
     action
    -0.62
     poly
    -0.62
     dr
    -0.62
     tying
    -0.62
     deb
    -0.61
     tri
    -0.60
     tra
    -0.59
    POSITIVE LOGITS
    erved
    4.44
    erving
    2.69
    erves
    2.53
    erve
    2.43
    ervation
    1.94
    erv
    1.67
    aturally
    1.37
    served
    1.36
    erver
    1.21
    ledged
    1.14
    Activations Density 0.013%

    No Known Activations