© 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. 17105
    Prev
    Next
    INDEX
    Explanations

    words related to sequences, orders, or events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "precede" and its variations

    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
    Hub
    -0.69
    hub
    -0.68
    Fair
    -0.67
    zie
    -0.67
    arov
    -0.67
    gal
    -0.65
    erm
    -0.63
    activation
    -0.62
     Beautiful
    -0.62
    raq
    -0.61
    POSITIVE LOGITS
     preceded
    0.91
     preced
    0.89
    icter
    0.85
    ebin
    0.77
    pend
    0.74
    ptions
    0.69
     precedence
    0.69
    imes
    0.68
    ocument
    0.66
     tempted
    0.65
    Activations Density 0.013%

    No Known Activations