© 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. 7-RES-JB
    11. 23021
    Prev
    Next
    INDEX
    Explanations

    strings related to technical coding, such as interstitial, gallery, thumbnails, and function calls

    oai_token-act-pair · gpt-3.5-turbo

    specific punctuation marks, especially commas and closing brackets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CBC
    -0.67
    udos
    -0.67
    ega
    -0.66
    kus
    -0.64
     Logged
    -0.64
    chin
    -0.63
    atch
    -0.61
    hib
    -0.60
    GM
    -0.60
    uberty
    -0.60
    POSITIVE LOGITS
    ooters
    0.87
     EntityItem
    0.73
    channelAvailability
    0.69
    ãĥł
    0.69
     partName
    0.68
     etc
    0.67
    mint
    0.64
    ricanes
    0.62
     whence
    0.62
    ãĥ«
    0.61
    Activations Density 0.041%

    No Known Activations