© 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. 2-RES-JB
    11. 11610
    Prev
    Next
    INDEX
    Explanations

    words related to a trend of decrease or deterioration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to trends in movement, specifically downward and upward changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Í
    -0.78
    Cu
    -0.74
    TOP
    -0.71
    ument
    -0.69
    illon
    -0.68
    roma
    -0.68
    mberg
    -0.67
    DN
    -0.67
    VA
    -0.67
    abase
    -0.66
    POSITIVE LOGITS
    ¥ŀ
    0.98
     trajectory
    0.89
    stairs
    0.88
     spiral
    0.88
     earthqu
    0.87
     downward
    0.87
     srf
    0.86
     traject
    0.85
     slopes
    0.81
     upward
    0.81
    Activations Density 0.010%

    No Known Activations