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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17739
    Prev
    Next
    INDEX
    Explanations

    tweets made by different individuals

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating tweets or social media posts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    士
    -0.76
    bred
    -0.70
    ulhu
    -0.66
    phal
    -0.64
    姫
    -0.61
    ricular
    -0.61
     Trials
    -0.60
    vette
    -0.59
    zik
    -0.59
    riks
    -0.59
    POSITIVE LOGITS
     "@
    0.90
    realDonaldTrump
    0.83
     hasht
    0.83
    weet
    0.83
    URL
    0.80
     tweets
    0.80
     hashtag
    0.78
    ITCH
    0.75
    Tweet
    0.75
     condol
    0.72
    Activations Density 0.034%

    No Known Activations