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. 11-RES-JB
    6. 8833
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to computer hardware components and models

    oai_token-act-pair · gpt-3.5-turbo

    specific model names and specifications of electronic devices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sts
    -0.77
     fle
    -0.76
     bree
    -0.75
     Theo
    -0.72
     dred
    -0.71
     Haitian
    -0.71
     Somali
    -0.68
     cler
    -0.67
     snatch
    -0.67
     batters
    -0.65
    POSITIVE LOGITS
    Device
    1.18
    710
    1.13
    Sense
    1.13
     chipset
    1.12
    Display
    1.11
    Battery
    1.11
    Pixel
    1.10
    850
    1.09
    920
    1.09
    Samsung
    1.09
    Activations Density 0.194%

    No Known Activations