© 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. 9-RES-JB
    11. 14132
    Prev
    Next
    INDEX
    Explanations

    phrases related to attempts and outcomes

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating failure or lack of success

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.75
    éĹĺ
    -0.74
    ËĪ
    -0.66
    ku
    -0.63
    Secondly
    -0.61
    asus
    -0.61
    Introdu
    -0.59
     Introdu
    -0.59
     Ded
    -0.58
    CHAPTER
    -0.58
    POSITIVE LOGITS
     results
    1.40
     success
    1.37
    success
    1.36
     unsuccessful
    1.26
    results
    1.23
    successful
    1.21
    successfully
    1.16
     successes
    1.14
     succeeds
    1.14
     result
    1.13
    Activations Density 1.199%

    No Known Activations