© 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. 504
    Prev
    Next
    INDEX
    Explanations

    phrases related to showing concern or interest for someone or something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to care and concern

    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
     confirmation
    -0.76
     prohibition
    -0.73
     transcript
    -0.69
    ãĥĪ
    -0.68
     resumes
    -0.66
    oute
    -0.65
     resume
    -0.65
     replacements
    -0.62
     Yugoslavia
    -0.61
     conclusion
    -0.61
    POSITIVE LOGITS
    taker
    1.05
     cared
    1.04
    lessly
    0.95
     passionately
    0.90
    giving
    0.77
    lington
    0.73
    lest
    0.73
    lessness
    0.71
    borgh
    0.70
    bear
    0.70
    Activations Density 0.018%

    No Known Activations