© 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. 3038
    Prev
    Next
    INDEX
    Explanations

    family relationships, specifically focusing on in-laws

    oai_token-act-pair · gpt-3.5-turbo

    references to familial relationships, particularly those involving in-laws

    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
    PDATE
    -0.83
    izoph
    -0.79
    anche
    -0.77
    ific
    -0.71
    pure
    -0.70
    pless
    -0.68
    arak
    -0.68
    istor
    -0.68
    OVER
    -0.67
    imester
    -0.66
    POSITIVE LOGITS
    hood
    0.79
     Jav
    0.76
     Jeffrey
    0.72
     Sergei
    0.72
     Cheney
    0.72
     Sergey
    0.72
     Louis
    0.72
     who
    0.72
     Angelo
    0.72
     José
    0.71
    Activations Density 0.047%

    No Known Activations