© 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. 6-RES-JB
    11. 17734
    Prev
    Next
    INDEX
    Explanations

    instances where individuals express thoughts or feelings about a particular topic

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing possession or ownership

    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
     Vog
    -0.73
    unker
    -0.69
     Carbuncle
    -0.68
     Lyndon
    -0.68
     Hutch
    -0.68
    haus
    -0.65
     Lerner
    -0.65
     Rowling
    -0.65
     Osc
    -0.65
     Rudolph
    -0.63
    POSITIVE LOGITS
     own
    1.57
    self
    1.07
     condolences
    1.03
    selves
    0.96
     Own
    0.95
     favourite
    0.95
     thoughts
    0.93
     displeasure
    0.92
     preferred
    0.90
     resignation
    0.89
    Activations Density 0.219%

    No Known Activations