© 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. 1-RES-JB
    11. 8604
    Prev
    Next
    INDEX
    Explanations

    phrases related to ownership or possession

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĥ
    -0.76
    AFTA
    -0.68
    çīĪ
    -0.68
     EFF
    -0.67
     externalToEVAOnly
    -0.67
    ETHOD
    -0.67
     ABE
    -0.66
    utical
    -0.64
    ä¸Ń
    -0.64
     ÙĪ
    -0.64
    POSITIVE LOGITS
     Own
    1.12
    ed
    0.97
    Own
    0.94
    est
    0.92
    ories
    0.88
    ership
    0.86
    ners
    0.80
    ner
    0.79
    imate
    0.78
    emouth
    0.78
    Activations Density 0.020%

    No Known Activations