© 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. 5084
    Prev
    Next
    INDEX
    Explanations

    problems and causes related to technical issues or physical malfunctions

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating problems and their causes

    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
    robe
    -0.83
    ongyang
    -0.69
     commissions
    -0.68
    ACP
    -0.68
     nods
    -0.67
     laureate
    -0.66
     ceremonies
    -0.66
    winner
    -0.65
    cyclop
    -0.65
    uart
    -0.65
    POSITIVE LOGITS
     plag
    1.42
     caused
    1.25
     exacerbated
    1.19
     worsened
    1.17
     plague
    1.10
     Symptoms
    1.08
     symptoms
    1.05
     worsen
    1.04
     severity
    1.02
    Sym
    0.99
    Activations Density 0.965%

    No Known Activations