© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 20430
    Prev
    Next
    INDEX
    Explanations

    Twitter URLs

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "com" in various contexts, likely related to web addresses or social media

    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
    ĪĴ
    -0.93
     Balt
    -0.74
     Frie
    -0.66
    luster
    -0.64
    ãĤ¹ãĥĪ
    -0.63
    İĭ
    -0.62
    oring
    -0.61
    quartered
    -0.59
     Loud
    -0.59
     Philips
    -0.59
    POSITIVE LOGITS
    au
    0.76
    ike
    0.76
    /_
    0.73
    cdn
    0.72
    twitter
    0.72
    biz
    0.72
    nz
    0.71
    ierre
    0.70
    ua
    0.70
    /?
    0.70
    Activations Density 0.023%

    No Known Activations