© 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. 6844
    Prev
    Next
    INDEX
    Explanations

    terms related to technical issues such as memory leaks, corrosion, distraction, mold, pollution, and dehydration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to issues and problems caused by various types of leaks and pollutants

    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
     Macron
    -0.71
    Cash
    -0.67
     WIN
    -0.67
    ramid
    -0.65
    esson
    -0.63
    rolet
    -0.62
    endor
    -0.61
    ij
    -0.61
     PUR
    -0.61
    vez
    -0.61
    POSITIVE LOGITS
     prevention
    1.24
     plag
    1.20
     Symptoms
    1.14
     caused
    1.14
     plague
    1.09
     Detected
    1.09
     Prevention
    1.07
     symptoms
    1.06
     ridden
    1.05
    prone
    1.02
    Activations Density 0.587%

    No Known Activations