© 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. 9924
    Prev
    Next
    INDEX
    Explanations

    dates in the format month day, year

    oai_token-act-pair · gpt-3.5-turbo

    sequences of numbers, dates, and social media handles

    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
     prosec
    -0.80
     disciplines
    -0.80
     covenant
    -0.78
     accelerator
    -0.77
     edged
    -0.75
     displacement
    -0.74
    ¥ŀ
    -0.73
     concentrated
    -0.73
     allied
    -0.73
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.73
    POSITIVE LOGITS
    https
    1.48
    Advertisement
    1.47
    RIP
    1.47
    Twitter
    1.46
    Advertisements
    1.45
    Wow
    1.39
    Loading
    1.39
    Tumblr
    1.38
    Congratulations
    1.35
    Screenshot
    1.34
    Activations Density 0.441%

    No Known Activations