© 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. 22078
    Prev
    Next
    INDEX
    Explanations

    technical or specialized terminologies related to various industries and fields

    oai_token-act-pair · gpt-3.5-turbo

    diverse categories of items and entities, including sports, fashion, and topics related to social issues

    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
    rawdownloadcloneembedreportprint
    -0.78
     Kub
    -0.72
     Tale
    -0.68
    Reviewer
    -0.67
    quickShipAvailable
    -0.66
    \":
    -0.66
     Moz
    -0.65
    pmwiki
    -0.64
     "$:/
    -0.62
    ãģ®ç
    -0.61
    POSITIVE LOGITS
    venge
    1.02
     extent
    0.89
     detriment
    0.79
    perate
    0.79
     coffers
    0.77
     destinations
    0.76
    livion
    0.76
    rouse
    0.75
     converter
    0.74
    levels
    0.71
    Activations Density 1.259%

    No Known Activations