© 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. 7127
    Prev
    Next
    INDEX
    Explanations

    phrases related to newsletter editors and their notes

    oai_token-act-pair · gpt-3.5-turbo

    references to editorial notes or announcements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    yip
    -0.81
    ĪĴ
    -0.71
    Downloadha
    -0.71
    jri
    -0.70
    odka
    -0.68
    plings
    -0.67
    philis
    -0.67
    opian
    -0.67
     contagious
    -0.66
     plaus
    -0.66
    POSITIVE LOGITS
     Cosponsors
    0.82
    Publisher
    0.79
     Picks
    0.78
     Guild
    0.76
    olkien
    0.76
    iquette
    0.76
     Aires
    0.73
    ×ķ
    0.72
    ãĤ¨ãĥ«
    0.71
    ãĥ³ãĤ¸
    0.71
    Activations Density 0.268%

    No Known Activations