© 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. 8-RES-JB
    6. 376
    Prev
    Next
    INDEX
    Explanations

    percentages or numerical values expressed as a percentage

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate percentages

    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
    ALLY
    -0.81
    kefeller
    -0.76
     Dull
    -0.74
    PORT
    -0.73
    GROUP
    -0.72
    Merit
    -0.71
    Attributes
    -0.71
    IDES
    -0.69
    ITED
    -0.68
    OULD
    -0.66
    POSITIVE LOGITS
    imet
    1.40
    imeter
    1.12
    uation
    0.75
    uary
    0.74
    enary
    0.73
    urance
    0.73
     occupancy
    0.71
    rate
    0.70
    xual
    0.70
     humidity
    0.69
    Activations Density 0.042%

    No Known Activations