© 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. 3-RES-JB
    11. 13068
    Prev
    Next
    INDEX
    Explanations

    references to literary works and projects

    oai_token-act-pair · gpt-3.5-turbo

    references to genres or types of media, particularly in relation to storytelling elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niet
    -0.78
     Petraeus
    -0.69
    furt
    -0.66
     Holder
    -0.62
     Kissinger
    -0.59
     Berks
    -0.59
     Gest
    -0.59
     Oval
    -0.58
     Bernstein
    -0.58
     Able
    -0.57
    POSITIVE LOGITS
     dracon
    0.69
    theless
    0.67
    ovember
    0.66
    taboola
    0.65
    oby
    0.63
     hereby
    0.62
    mosp
    0.61
    ^{
    0.61
    */(
    0.60
    Downloadha
    0.60
    Activations Density 1.096%

    No Known Activations