© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 21188
    Prev
    Next
    INDEX
    Explanations

    phrases related to rights or policies affecting specific groups of people

    oai_token-act-pair · gpt-3.5-turbo

    references to marginalized or specific groups of people

    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
    ob
    -0.76
    ILY
    -0.67
    enegger
    -0.65
    ointment
    -0.63
     Hang
    -0.63
    âĺħâĺħ
    -0.62
     Serpent
    -0.62
    irth
    -0.61
    OB
    -0.61
    bang
    -0.61
    POSITIVE LOGITS
     wishing
    0.98
     who
    0.87
     kinds
    0.84
     pesky
    0.84
     interested
    0.83
     affected
    0.77
     attending
    0.77
     surveyed
    0.74
     advocating
    0.74
     victimized
    0.73
    Activations Density 0.068%

    No Known Activations