© 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. 6-RES-JB
    11. 22465
    Prev
    Next
    INDEX
    Explanations

    the word "do" followed by actions or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "I do."

    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
     Handling
    -0.75
    fields
    -0.69
     Entered
    -0.63
    hog
    -0.63
     Madagascar
    -0.62
     Rah
    -0.62
    case
    -0.61
    ware
    -0.60
     Ages
    -0.60
     Pyongyang
    -0.59
    POSITIVE LOGITS
    pez
    0.99
    omsday
    0.92
    ppel
    0.91
    herty
    0.84
    女
    0.84
    lez
    0.83
    oley
    0.82
    vet
    0.82
    ggy
    0.78
    onga
    0.77
    Activations Density 0.114%

    No Known Activations