© 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. 22473
    Prev
    Next
    INDEX
    Explanations

    phrases indicating possession or association

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms of words, particularly related to ownership or attribution in a narrative context

    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
    Reviewer
    -0.90
    Fed
    -0.79
    Compare
    -0.78
    gpu
    -0.78
    ISO
    -0.73
    Copyright
    -0.73
    Streamer
    -0.72
    ãĥĦ
    -0.71
    Sanders
    -0.71
    Resources
    -0.70
    POSITIVE LOGITS
     grandson
    1.01
     successor
    0.93
     tenure
    0.91
     autobiography
    0.91
     infamous
    0.91
     legacy
    0.90
     seminal
    0.88
     footsteps
    0.87
     granddaughter
    0.87
     son
    0.85
    Activations Density 0.214%

    No Known Activations