© 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. 6-RES-JB
    11. 17085
    Prev
    Next
    INDEX
    Explanations

    mentions of physical descriptions of individuals, particularly focusing on their appearance

    oai_token-act-pair · gpt-3.5-turbo

    information related to ancestry and physical characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     takedown
    -0.79
    uer
    -0.70
    uers
    -0.68
     progress
    -0.67
     escal
    -0.66
     evaluates
    -0.66
    casters
    -0.65
    ousse
    -0.64
    ior
    -0.64
    olving
    -0.64
    POSITIVE LOGITS
     Caucasian
    0.98
     surname
    0.92
     Caucas
    0.85
     aunt
    0.81
     surn
    0.80
     eldest
    0.79
     Gujar
    0.77
     Cherokee
    0.76
     nephew
    0.76
     married
    0.76
    Activations Density 0.398%

    No Known Activations