© 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. 22488
    Prev
    Next
    INDEX
    Explanations

    positive words conveying support or encouragement

    oai_token-act-pair · gpt-3.5-turbo

    recurrent phrases and expressions emphasizing longevity or continuity

    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
     agre
    -0.66
     seiz
    -0.65
    ét
    -0.62
     rul
    -0.62
     accomp
    -0.61
     unden
    -0.59
     territ
    -0.59
     awa
    -0.59
     laun
    -0.59
    »
    -0.59
    POSITIVE LOGITS
     Anti
    0.58
     Straw
    0.57
     Fire
    0.56
     Coca
    0.56
     Coffee
    0.55
     coffee
    0.55
     Burg
    0.54
     bully
    0.53
     Kelvin
    0.52
    icrobial
    0.52
    Activations Density 0.935%

    No Known Activations