© 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. 6-RES-JB
    11. 20628
    Prev
    Next
    INDEX
    Explanations

    numerical values in the thousands

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of numerical values or quantities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :(
    -0.69
     builder
    -0.58
     deed
    -0.58
     deeds
    -0.57
     resemblance
    -0.56
    soever
    -0.56
     pregn
    -0.55
    asma
    -0.55
     Toast
    -0.54
     XD
    -0.54
    POSITIVE LOGITS
    000
    1.57
    700
    1.10
    500
    1.04
    600
    1.03
    800
    1.03
    00
    1.02
    900
    0.98
    400
    0.98
    300
    0.91
    200
    0.88
    Activations Density 0.099%

    No Known Activations