© 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. 17071
    Prev
    Next
    INDEX
    Explanations

    references to a daily newsletter or dispatch service

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "dispatch"

    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
    unal
    -0.77
    umber
    -0.75
    abase
    -0.74
    ghazi
    -0.73
    egal
    -0.70
    urt
    -0.70
    rd
    -0.69
    ipedia
    -0.67
    basketball
    -0.67
    imar
    -0.66
    POSITIVE LOGITS
     Dispatch
    1.03
    Dispatch
    0.98
     dispatch
    0.87
    DragonMagazine
    0.83
    hyde
    0.81
    Queue
    0.77
    ©¶æ¥µ
    0.76
    ables
    0.74
    ivery
    0.73
    ãĥ¼ãĥĨãĤ£
    0.70
    Activations Density 0.013%

    No Known Activations