© 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. 8-RES-JB
    11. 22528
    Prev
    Next
    INDEX
    Explanations

    phrases related to societal norms and behavior

    oai_token-act-pair · gpt-3.5-turbo

    negative assertions about gender dynamics and societal roles

    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
    iHUD
    -0.76
    Chain
    -0.69
    hent
    -0.66
     predecessor
    -0.65
    éĹ
    -0.64
    someone
    -0.64
    client
    -0.62
    ainment
    -0.62
    plate
    -0.61
    holder
    -0.61
    POSITIVE LOGITS
     outnumbered
    1.07
     disproportionately
    1.05
    joice
    0.96
     rejoice
    0.90
     overwhelmingly
    0.89
     flock
    0.87
     dominate
    0.86
     smarter
    0.84
     behave
    0.84
     enslaved
    0.84
    Activations Density 0.621%

    No Known Activations