© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    6. 6550
    Prev
    Next
    INDEX
    Explanations

    social media platform names containing the word "umble"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "umble," particularly in various contexts and combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arians
    -0.85
    pherd
    -0.83
    ohn
    -0.79
    ning
    -0.77
    olan
    -0.74
    ablishment
    -0.72
    agar
    -0.68
    istered
    -0.68
    ewski
    -0.67
    hips
    -0.67
    POSITIVE LOGITS
    Upon
    1.10
    bee
    1.02
    weed
    0.98
    bles
    0.92
    butt
    0.85
    ble
    0.85
    bly
    0.82
     Bundle
    0.80
    upon
    0.80
    BLE
    0.76
    Activations Density 0.072%

    No Known Activations