© 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. 4-RES-JB
    11. 8518
    Prev
    Next
    INDEX
    Explanations

    questions starting with "Did"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Did" indicating questions or inquiries

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

    No Comments

    Negative Logits
    heter
    -0.75
    stood
    -0.75
    arters
    -0.73
    projects
    -0.72
    thur
    -0.71
    washer
    -0.70
    houses
    -0.69
    Tai
    -0.68
     Methods
    -0.67
    rooms
    -0.66
    POSITIVE LOGITS
    actic
    0.94
    iosyncr
    0.83
    nt
    0.79
    netflix
    0.76
     not
    0.72
    ĸļ
    0.71
    eredith
    0.71
    omorphic
    0.68
     mislead
    0.66
     originate
    0.66
    Activations Density 0.033%

    No Known Activations