Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4650
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Sabour" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    repeated patterns or specific letter combinations in words

    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
     cryst
    -0.62
     Forbidden
    -0.60
     Millenn
    -0.60
     balloons
    -0.59
    ITNESS
    -0.58
    Initialized
    -0.58
     charitable
    -0.58
     inertia
    -0.58
     conscientious
    -0.57
     hel
    -0.57
    POSITIVE LOGITS
    elli
    1.04
    ooth
    0.93
    ella
    0.93
    ovsky
    0.90
    ovich
    0.88
    anski
    0.85
    ati
    0.85
    ote
    0.84
    ela
    0.83
    etz
    0.83
    Activations Density 0.212%

    No Known Activations