© 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. 2-RES-JB
    11. 13983
    Prev
    Next
    INDEX
    Explanations

    phrases related to consecutive events or occurrences

    oai_token-act-pair · gpt-3.5-turbo

    references to consecutive events or terms related to continuity and succession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ARP
    -0.80
    ruck
    -0.78
    acea
    -0.77
    rolling
    -0.76
    OH
    -0.73
    Lake
    -0.71
    VL
    -0.70
    iger
    -0.69
    lua
    -0.68
    BAT
    -0.67
    POSITIVE LOGITS
     successive
    1.34
     generations
    1.02
    wcs
    0.95
    ĸļ
    0.93
     incarn
    0.90
     administrations
    0.89
     subsequ
    0.87
     strugg
    0.87
     conceptions
    0.86
     iterations
    0.86
    Activations Density 0.010%

    No Known Activations