© 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. 8-RES-JB
    11. 17202
    Prev
    Next
    INDEX
    Explanations

    specific mentions of legislation or legal actions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Under" followed by numerical 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
     frivol
    -0.63
    aukee
    -0.62
     gor
    -0.62
     distur
    -0.61
     bracelet
    -0.61
     bout
    -0.59
     mov
    -0.59
    ospace
    -0.59
    okia
    -0.59
    auga
    -0.58
    POSITIVE LOGITS
    neath
    1.43
    lying
    1.18
    mining
    1.11
    graduate
    1.08
    stand
    1.05
    cover
    1.03
    stood
    1.03
    statement
    1.02
    reporting
    0.97
    written
    0.96
    Activations Density 0.036%

    No Known Activations