© 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. 8-RES-JB
    11. 6499
    Prev
    Next
    INDEX
    Explanations

    phrases related to expertise and leadership

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating expertise and significant occurrences or changes in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     expire
    -0.50
    stood
    -0.49
     slightest
    -0.47
     Likes
    -0.46
    ById
    -0.46
    ppers
    -0.45
     throats
    -0.45
    ãĥĥãĥī
    -0.44
    umably
    -0.44
    licks
    -0.44
    POSITIVE LOGITS
     regarding
    0.70
    DragonMagazine
    0.66
     of
    0.64
     concerning
    0.63
     relating
    0.61
     wherein
    0.60
     whereby
    0.60
     illustrating
    0.56
    UTH
    0.54
     linking
    0.53
    Activations Density 1.002%

    No Known Activations