© 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. 7-RES-JB
    11. 12513
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of "hangover"

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of "over"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gerald
    -0.70
    sonian
    -0.69
    ANY
    -0.64
    merga
    -0.64
    tiny
    -0.63
    haps
    -0.62
    DEF
    -0.62
    ENN
    -0.61
    aft
    -0.61
    omed
    -0.61
    POSITIVE LOGITS
     scenario
    0.75
     queen
    0.68
    vention
    0.68
     mechanism
    0.68
     clause
    0.66
     Clause
    0.65
     Savior
    0.63
    heid
    0.63
    eering
    0.63
     syndrome
    0.62
    Activations Density 0.069%

    No Known Activations