© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 4812
    Prev
    Next
    INDEX
    Explanations

    the word "Several" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "Several," indicating the mention of multiple items or occurrences

    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
    Interstitial
    -0.71
    arial
    -0.62
    opl
    -0.60
    ocracy
    -0.59
    cum
    -0.59
    âĹ¼
    -0.58
    existent
    -0.57
    omo
    -0.57
     widest
    -0.56
    oper
    -0.54
    POSITIVE LOGITS
    een
    0.93
     Hours
    0.65
     Steps
    0.64
    theless
    0.63
     Ways
    0.62
     reports
    0.61
    eteen
    0.60
     cheers
    0.59
    inguished
    0.59
    nces
    0.59
    Activations Density 0.142%

    No Known Activations