© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 23489
    Prev
    Next
    INDEX
    Explanations

    Twitter handles followed by specific dates as well as actions or events related to those Twitter handles

    oai_token-act-pair · gpt-3.5-turbo

    parentheses in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    icion
    -0.74
    £ı
    -0.73
    naires
    -0.65
    zed
    -0.64
    ients
    -0.62
    naire
    -0.60
    Reviewer
    -0.60
    én
    -0.60
    Ĥª
    -0.60
    Ĥ¬
    -0.59
    POSITIVE LOGITS
     December
    1.52
     October
    1.51
     September
    1.50
     February
    1.50
     November
    1.49
     January
    1.46
     August
    1.45
     June
    1.45
     April
    1.44
     July
    1.43
    Activations Density 0.024%

    No Known Activations