© 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. 6-RES-JB
    11. 3561
    Prev
    Next
    INDEX
    Explanations

    phrases with the word "which" followed by a subject or object

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of delimiters or punctuation, specifically the end of text markers

    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
     Vaugh
    -0.68
     Seym
    -0.67
     Niet
    -0.60
    Instead
    -0.60
     Darling
    -0.58
    Fram
    -0.57
    Tokens
    -0.57
     Frie
    -0.56
     disadvant
    -0.55
    Daddy
    -0.54
    POSITIVE LOGITS
    zbollah
    0.82
    ersive
    0.70
    imes
    0.62
     awaits
    0.61
    ims
    0.60
     awaited
    0.60
     rejo
    0.60
    embed
    0.60
    ;;;;;;;;;;;;
    0.59
    usalem
    0.59
    Activations Density 0.097%

    No Known Activations