Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 8685
    Prev
    Next
    INDEX
    Explanations

    technical details and specifications related to electronic devices

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Huss
    -0.63
     Witt
    -0.62
     informal
    -0.59
     McH
    -0.59
     satir
    -0.58
     Beir
    -0.58
     derogatory
    -0.58
    sted
    -0.57
    mens
    -0.57
     lett
    -0.57
    POSITIVE LOGITS
     chipset
    1.31
     USB
    1.24
     firmware
    1.22
     BIOS
    1.20
     motherboard
    1.17
     SSD
    1.15
     ASUS
    1.15
    USB
    1.14
     HDMI
    1.13
     SATA
    1.11
    Activations Density 0.683%

    No Known Activations