© 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. 8887
    Prev
    Next
    INDEX
    Explanations

    phrases related to unsuccessful attempts or actions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "failed" and its variations in different contexts

    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
    leans
    -0.72
    olon
    -0.69
    etus
    -0.65
    lean
    -0.65
    wine
    -0.64
    rete
    -0.64
    aler
    -0.63
    andise
    -0.63
    CU
    -0.62
    addle
    -0.60
    POSITIVE LOGITS
     miser
    1.37
     spectacular
    0.95
     catast
    0.87
     horribly
    0.83
     muster
    0.82
     altogether
    0.81
     satisf
    0.76
     dism
    0.73
     because
    0.72
     disastrous
    0.71
    Activations Density 0.185%

    No Known Activations