© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 12270
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership or relationships

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to personal relationships and social interactions

    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
    ribune
    -0.83
    rors
    -0.78
    redd
    -0.74
    fect
    -0.73
    )+
    -0.69
    arte
    -0.69
    nance
    -0.68
    ante
    -0.67
    amin
    -0.66
    raf
    -0.65
    POSITIVE LOGITS
     parted
    0.97
     together
    0.97
     Together
    0.96
     insepar
    0.94
     mutually
    0.90
     reunion
    0.86
     chatting
    0.83
    emate
    0.82
     toget
    0.82
     mutual
    0.81
    Activations Density 0.561%

    No Known Activations