© 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. 10685
    Prev
    Next
    INDEX
    Explanations

    mentions or references to "cases", possibly with numbers or specific details

    oai_token-act-pair · gpt-3.5-turbo

    terms related to nuts and cashew products

    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
     anten
    -0.73
     Kardashian
    -0.64
    ĺħ
    -0.64
    ROR
    -0.63
    ¿½
    -0.62
     dear
    -0.62
     Naked
    -0.61
     Europa
    -0.60
     Generation
    -0.60
     Shack
    -0.59
    POSITIVE LOGITS
     cas
    1.07
    hew
    1.02
    hews
    0.93
    etime
    0.93
    grain
    0.90
    emate
    0.90
    ificial
    0.89
    ques
    0.89
    ework
    0.87
    eless
    0.84
    Activations Density 0.012%

    No Known Activations