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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 20275
    Prev
    Next
    INDEX
    Explanations

    words related to software commands or coding instructions

    oai_token-act-pair · gpt-3.5-turbo

    instances of numerical or statistical references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hement
    -0.89
     brunt
    -0.69
     scrap
    -0.61
     WRITE
    -0.60
     intending
    -0.58
     estranged
    -0.58
    iott
    -0.58
     advertisers
    -0.57
     Dollar
    -0.57
     inund
    -0.56
    POSITIVE LOGITS
    ³³³
    0.93
    ³³³³³³³³³³³³³³³³
    0.88
    ³³³³³³³³
    0.86
    ³³³³
    0.84
    PRESS
    0.78
    FactoryReloaded
    0.78
    ³³
    0.77
    BuyableInstoreAndOnline
    0.75
    SCP
    0.75
    00200000
    0.75
    Activations Density 0.261%

    No Known Activations