© 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. 12633
    Prev
    Next
    INDEX
    Explanations

    medical terms or conditions related to occurrences happening unexpectedly

    oai_token-act-pair · gpt-3.5-turbo

    words related to accidents or accidental occurrences

    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
    PB
    -0.80
    SHIP
    -0.77
    geist
    -0.69
    SG
    -0.69
    PT
    -0.68
    JV
    -0.68
     hope
    -0.66
    ben
    -0.63
    ger
    -0.63
    senal
    -0.62
    POSITIVE LOGITS
    redited
    1.30
    uracy
    1.27
    acc
    1.07
    urate
    1.06
    identally
    1.03
    ustomed
    0.99
    reditation
    0.99
    idental
    0.96
    urrency
    0.95
    amation
    0.94
    Activations Density 0.005%

    No Known Activations