© 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. 1-RES-JB
    11. 3805
    Prev
    Next
    INDEX
    Explanations

    specific names and terms, possibly related to news or articles

    oai_token-act-pair · gpt-3.5-turbo

    instances of the proper noun "Berger" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mons
    -0.68
    vertisement
    -0.66
    lesiastical
    -0.65
    Spread
    -0.64
    Mega
    -0.63
     Socrates
    -0.62
    ptoms
    -0.62
    favorite
    -0.60
     Maximum
    -0.59
    ishly
    -0.58
    POSITIVE LOGITS
    ãĤ´ãĥ³
    0.90
    heast
    0.85
    heastern
    0.84
    é¾
    0.82
    erker
    0.77
    ettings
    0.76
    orious
    0.73
    cest
    0.73
    acci
    0.73
    terday
    0.73
    Activations Density 0.024%

    No Known Activations