© 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. 6309
    Prev
    Next
    INDEX
    Explanations

    references to online articles and social media interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sentences related to news articles and opinions on Twitter

    oai_token-act-pair · gpt-3.5-turbo
    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
    ahime
    -0.62
     Tycoon
    -0.51
     Gamble
    -0.50
     rebuilt
    -0.49
     destro
    -0.49
     fitt
    -0.48
     subsistence
    -0.48
    peat
    -0.47
    dollar
    -0.46
    amina
    -0.46
    POSITIVE LOGITS
     transcripts
    0.62
     publication
    0.60
     reader
    0.59
     redacted
    0.59
     Pastebin
    0.59
     captcha
    0.58
     quotation
    0.58
     acron
    0.58
     retweet
    0.57
     quoting
    0.57
    Activations Density 2.968%

    No Known Activations