© 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. 20804
    Prev
    Next
    INDEX
    Explanations

    phrases related to prolonged or extended durations of time

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "extended" in various contexts

    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
    士
    -0.85
    mir
    -0.79
    lean
    -0.79
    tery
    -0.77
    powder
    -0.76
    Maker
    -0.76
    fighter
    -0.75
    kie
    -0.74
    Hide
    -0.74
    Submit
    -0.73
    POSITIVE LOGITS
     adolesc
    1.07
     periods
    0.90
     therap
    0.90
     satell
    0.83
     warranties
    0.82
     maturity
    0.81
     frontal
    0.80
     subsequ
    0.79
     arrangements
    0.79
     lengths
    0.79
    Activations Density 0.009%

    No Known Activations