© 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. 7-RES-JB
    11. 20778
    Prev
    Next
    INDEX
    Explanations

    the phrase "old", especially when referring to traditional or familiar things

    oai_token-act-pair · gpt-3.5-turbo

    references to traditional or nostalgic concepts

    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
    pedia
    -0.88
    pta
    -0.85
    endant
    -0.78
    emis
    -0.76
    emi
    -0.75
    endants
    -0.69
     ende
    -0.67
    mos
    -0.65
    idelines
    -0.65
    omon
    -0.65
    POSITIVE LOGITS
     fashioned
    0.96
     ol
    0.84
    fashioned
    0.77
     Victorian
    0.70
     Wrath
    0.67
     brute
    0.67
     gentleman
    0.66
     Hog
    0.66
     Rip
    0.65
     old
    0.63
    Activations Density 0.116%

    No Known Activations