© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 17877
    Prev
    Next
    INDEX
    Explanations

    phrases expressing confusion or frustration

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various 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
    worn
    -0.77
    ignt
    -0.76
    alus
    -0.74
    hyde
    -0.74
    dropping
    -0.69
    onduct
    -0.69
    lived
    -0.68
    staking
    -0.67
    culosis
    -0.67
    imb
    -0.66
    POSITIVE LOGITS
     heck
    1.68
     hell
    1.52
     fuck
    1.28
     fuss
    1.23
     HELL
    0.91
     difference
    0.87
     future
    0.86
     ramifications
    0.83
     consequences
    0.83
     average
    0.83
    Activations Density 0.089%

    No Known Activations