© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9241
    Prev
    Next
    INDEX
    Explanations

    calls to action related to subscribing or taking actions

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express capability or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tons
    -0.57
    FTWARE
    -0.55
    need
    -0.54
     Falls
    -0.52
     Photoshop
    -0.51
    ered
    -0.50
     Need
    -0.49
    cano
    -0.47
    got
    -0.47
    went
    -0.46
    POSITIVE LOGITS
    ILE
    0.60
    merga
    0.59
    acy
    0.56
    ãĥİ
    0.55
    ete
    0.53
    ãĤ¨
    0.53
    idy
    0.48
    ãĥª
    0.48
    bleacher
    0.47
    pled
    0.47
    Activations Density 0.047%

    No Known Activations