© 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. 13542
    Prev
    Next
    INDEX
    Explanations

    numeric data trends, indicating increases or decreases in values over time or between different periods

    oai_token-act-pair · gpt-3.5-turbo

    changes in statistics or numerical trends, particularly increases or decreases

    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
     masses
    -0.67
    gom
    -0.61
     GENERAL
    -0.60
    hai
    -0.55
    gram
    -0.55
    mop
    -0.55
    mins
    -0.54
    ²¾
    -0.54
     uncontroll
    -0.53
    bred
    -0.53
    POSITIVE LOGITS
     sharply
    0.87
     compared
    0.86
     marginally
    0.81
    amount
    0.75
    Sharp
    0.69
    actly
    0.69
    enhagen
    0.69
     substantially
    0.68
    Compare
    0.67
    Shar
    0.67
    Activations Density 0.107%

    No Known Activations