© 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. 11-RES-JB
    11. 23210
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical errors and troubleshooting

    oai_token-act-pair · gpt-3.5-turbo

    messages indicating errors or issues in a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tha
    -0.57
    itable
    -0.55
    gest
    -0.53
    berra
    -0.51
    bourne
    -0.48
     tongues
    -0.47
    wered
    -0.47
    ibrary
    -0.46
    roots
    -0.46
    Benef
    -0.46
    POSITIVE LOGITS
    IJ
    0.67
    »Ĵ
    0.64
    inction
    0.59
    Cola
    0.58
    erence
    0.55
    aign
    0.55
    «ĺ
    0.53
    ¦
    0.53
    ë
    0.53
    OSE
    0.52
    Activations Density 0.038%

    No Known Activations