© 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. 22315
    Prev
    Next
    INDEX
    Explanations

    phrases related to CDs and DVDs

    oai_token-act-pair · gpt-3.5-turbo

    references to CDs and DVDs

    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
    olulu
    -0.76
    nel
    -0.73
    Downloadha
    -0.70
    staking
    -0.67
    rely
    -0.64
    tenance
    -0.64
    skirts
    -0.64
     Aires
    -0.64
    chers
    -0.63
    ````
    -0.62
    POSITIVE LOGITS
    ROM
    1.01
    MX
    0.95
    NF
    0.94
    ouble
    0.94
    erning
    0.93
    MA
    0.90
    VD
    0.88
    irect
    0.87
    DL
    0.87
    NR
    0.86
    Activations Density 0.034%

    No Known Activations