© 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. 7-RES-JB
    11. 12698
    Prev
    Next
    INDEX
    Explanations

    technical terms related to IT and computer systems, particularly involving software or data management

    oai_token-act-pair · gpt-3.5-turbo

    references to specific advertisements or advertising (AD)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.72
    aceous
    -0.70
    ãĤ¡
    -0.68
    drop
    -0.68
     htt
    -0.67
    comes
    -0.67
    zzle
    -0.63
    andum
    -0.63
    toe
    -0.61
    ozyg
    -0.61
    POSITIVE LOGITS
    VERTISEMENT
    1.18
    VERTIS
    1.10
    MIN
    1.08
    vantage
    0.95
    VIS
    0.92
    ynasty
    0.90
    DR
    0.88
    venture
    0.87
    iamond
    0.87
    SI
    0.86
    Activations Density 0.023%

    No Known Activations