© 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. 17697
    Prev
    Next
    INDEX
    Explanations

    terms related to confidential information and data security

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to sensitive and personal information breaches

    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
     nomine
    -0.70
    FontSize
    -0.62
     conclud
    -0.62
    Management
    -0.61
     rounding
    -0.61
    Ü
    -0.60
    ovation
    -0.60
    staking
    -0.59
    aturation
    -0.59
    reporting
    -0.59
    POSITIVE LOGITS
     belongings
    1.00
     items
    0.98
     goodies
    0.93
    coins
    0.89
     goods
    0.84
     pieces
    0.82
     contents
    0.82
     treasures
    0.80
     materials
    0.80
     copies
    0.79
    Activations Density 1.028%

    No Known Activations