© 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. 10-RES-JB
    11. 5225
    Prev
    Next
    INDEX
    Explanations

    abstract concepts or actions described in a scientific or complex manner

    oai_token-act-pair · gpt-3.5-turbo

    active verbs and terms related to processes or changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     disappearing
    -0.66
     abound
    -0.65
    archment
    -0.62
     belonging
    -0.60
     stocking
    -0.57
     haven
    -0.57
    ittal
    -0.57
     supplementary
    -0.56
     branching
    -0.56
     dressing
    -0.55
    POSITIVE LOGITS
    ifies
    1.70
    izes
    1.65
    itates
    1.59
    ulates
    1.49
    tains
    1.44
    poses
    1.41
    iates
    1.39
    ends
    1.34
    ounces
    1.32
    uates
    1.30
    Activations Density 0.257%

    No Known Activations